Showing 1–50 of 125 results for author: Das, B

Universal Rendezvous of Anonymous Agents with Footprints

Authors: Bibhuti Das

Abstract: Deterministic rendezvous for two anonymous mobile agents starting simultaneously from two distinct nodes of an anonymous connected graph and navigating synchronously in the graph requires that they meet at some node. An instance of the rendezvous problem is the underlying graph, together with two distinct nodes that are the initial positions of the agents. Such an instance is said to be feasible i… ▽ More Deterministic rendezvous for two anonymous mobile agents starting simultaneously from two distinct nodes of an anonymous connected graph and navigating synchronously in the graph requires that they meet at some node. An instance of the rendezvous problem is the underlying graph, together with two distinct nodes that are the initial positions of the agents. Such an instance is said to be feasible if there is a deterministic algorithm guaranteeing rendezvous, possibly valid only for this instance. A rendezvous algorithm is said to be universal for a class of instances if it guarantees rendezvous for all feasible instances from this class. We consider the model with footprints: whenever an agent visits an unmarked node, it leaves a permanent footprint on it, and all footprints are identical. This paper aims at answering the open problem from the paper by Das and Pelc (SPAA 2026), asking whether there exists a universal rendezvous algorithm for the class of all instances in the model with footprints. We propose a universal rendezvous algorithm for the class of all instances where the underlying graph is connected (finite or countably infinite) in the model with footprints. This shows the existence of a universal algorithm for the class of all instances in the model with footprints, which is an affirmative answer to the open problem. △ Less

Submitted 9 August, 2026; originally announced August 2026.

Rendezvous of Mobile Deterministic Automata in Graphs

Authors: Bibhuti Das, Andrzej Pelc

Abstract: Two mobile agents, modeled as identical deterministic finite automata (DFA) navigating in synchronous rounds in a graph with unlabeled nodes, have to meet at some node. The well-researched task of meeting in a graph is known as rendezvous. Agents start at adversarially chosen distinct nodes in possibly different rounds. An instance of the rendezvous problem is the underlying graph, together with t… ▽ More Two mobile agents, modeled as identical deterministic finite automata (DFA) navigating in synchronous rounds in a graph with unlabeled nodes, have to meet at some node. The well-researched task of meeting in a graph is known as rendezvous. Agents start at adversarially chosen distinct nodes in possibly different rounds. An instance of the rendezvous problem is the underlying graph, together with the initial nodes $u$ and $v$ of the agents. Such an instance is feasible, if there exists a DFA (possibly working only for this instance), such that its identical copies starting at nodes $u$ and $v$, with an arbitrary delay, accomplish rendezvous. A DFA is RV-universal for a class of instances, if it guarantees rendezvous of its copies starting at the designated nodes with arbitrary delay, for all feasible instances of this class. Our goal is to investigate the existence of RV-universal DFA. We start by observing that if agents cannot mark nodes in any way then there does not exist a RV-universal DFA even for the class of instances where the underlying graph is a line. Hence we allow the use of identical pebbles to mark the nodes by the agents. We consider stationary pebbles that can be dropped by agents at nodes but cannot be picked up, and movable pebbles that can be dropped by agents and later picked up. We observe that, even in the more powerful scenario of movable pebbles, if agents are equipped with any finite number of pebbles, there is no RV-universal DFA for the class of all instances. Hence we restrict attention to instances where the underlying graph is a tree. Our main contribution are two contrasting results showing that movability of pebbles is a crucial feature. We first prove that for any finite number of stationary pebbles there is no RV-universal DFA for trees, and then we design a RV-universal DFA for trees, where each agent is equipped with a single movable pebble. △ Less

Submitted 6 August, 2026; originally announced August 2026.

From Decision to Random Certificates: Exponential Separation for Edge Estimation with Independent Set Queries

Authors: Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Gopinath Mishra

Abstract: We study the problem of estimating the number of edges in an undirected, unweighted graph using sublinear query access. We consider a query model that preserves the structure of Independent Set (IS) queries, but augments their output with a random certificate: given a vertex subset, the oracle returns a uniformly random edge from the induced subgraph if one exists, and returns null otherwise. Us… ▽ More We study the problem of estimating the number of edges in an undirected, unweighted graph using sublinear query access. We consider a query model that preserves the structure of Independent Set (IS) queries, but augments their output with a random certificate: given a vertex subset, the oracle returns a uniformly random edge from the induced subgraph if one exists, and returns null otherwise. Using this access, we give a randomized algorithm that outputs a $(1 \pm \varepsilon)$-approximation to the number of edges with constant success probability using $\widetilde{O}(\log^{2} m)$ queries. This implies an exponential separation from both standard IS queries and global random edge-sampling models: estimating the number of edges using standard IS queries require $\widetildeΘ\!\left(\min\left\{\sqrt{m},\, \frac{n}{\sqrt{m}}\right\}\right)$ queries, while direct random edge-sample access requires $\widetildeΘ(\sqrt{m})$ samples. Beyond separation in query complexity, our algorithm is output-sensitive: its query complexity is polylogarithmic in the number of edges in the graph. This aligns with the classical objective in group testing, where one seeks algorithms that are both worst-case optimal and instance-adaptive. Conceptually, our model connects group testing, the decision-versus-counting dichotomy, graph property testing, and the "power of a random certificate", and can be viewed as a structured form of conditional sampling of edges in graphs. △ Less

Submitted 8 July, 2026; originally announced July 2026.

A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories

Authors: Garima Jain, Abhijeet Patil, Surabhi Jain, Sanghamitra Pati, Amit Sethi, Sandeep Mathur, Pulkit Verma, Nishi Halduniya, Jatin Kashyap, Sharat Kumar, Simmi Kharb, Sunita Singh, Sucheta Devi Khuraijam, Sushma Khuraijam, Ratan Konjengbam, Arvind Kumar, Deepali Tirkey, Saurav Banerjee, Shivani Kalhan, Rakesh Kumar Gupta, Ranjana Solanki, Deepika Hemranjani, Shashank Nath Singh, Uma Handa, Manveen Kaur , et al. (14 additional authors not shown)

Abstract: We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa… ▽ More We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa (280 WSIs), scanned on a Hamamatsu NanoZoomer S360 at 40X magnification and 0.25 microns per pixel, and stored directly in NDPI format. Across the 470 WSIs, 446 WSIs contain annotated patch regions, yielding 7,398 PNG image patches with expert-verified C1 to C5 labels. The release includes NDPI WSIs, WSI-level GeoJSON annotation files, extracted patch images, deidentified metadata, a data dictionary, a validation summary, a manifest linking WSIs to Zenodo records, and code for dataset inspection and reuse. The complete dataset is approximately 950 GB and is available through Zenodo. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Comments: 9 pages, 1 figure

Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering

Authors: Shahnewaz Karim Sakib, Anindya Bijoy Das

Abstract: AI agents extend conventional large language model (LLM) applications by integrating language understanding with task execution, external tool use, and memory mechanisms. While memory allows agents to retain prior interactions and provide more personalized and context-aware responses, it also introduces a new vulnerability: information stored in memory can influence future outputs even when the cu… ▽ More AI agents extend conventional large language model (LLM) applications by integrating language understanding with task execution, external tool use, and memory mechanisms. While memory allows agents to retain prior interactions and provide more personalized and context-aware responses, it also introduces a new vulnerability: information stored in memory can influence future outputs even when the current query is clean. In this paper, we investigate memory manipulation in LLM-based agents for multiple-choice question answering. We first design and implement an LLM-based AI agent with an external memory component that stores and retrieves task-relevant information. We then introduce basic memory manipulation scenarios in which misleading or corrupted memories are inserted into the agent before it answers multiple-choice questions. Using a controlled experimental setup, we compare the agent's performance before and after memory manipulation and measure changes in answer accuracy, attack success rate, and selection of manipulated options. Our results show that even simple memory manipulations can noticeably affect the agent's final answers, causing it to select incorrect options despite receiving clean and well-formed questions. △ Less

Submitted 27 June, 2026; originally announced June 2026.

Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring

Authors: Shahnewaz Karim Sakib, Anindya Bijoy Das

Abstract: Multi-agent AI systems can improve answer selection by allowing different language models to exchange reasoning traces, revise initial predictions, and support a final decision. However, such communication may also introduce reliability risks: reasoning from one agent can correct another agent's mistake, but it can also mislead an agent that was initially correct. This paper studies reliable multi… ▽ More Multi-agent AI systems can improve answer selection by allowing different language models to exchange reasoning traces, revise initial predictions, and support a final decision. However, such communication may also introduce reliability risks: reasoning from one agent can correct another agent's mistake, but it can also mislead an agent that was initially correct. This paper studies reliable multi-agent AI communication through reasoning exchange and runtime answer revision. We develop a framework in which agents first answer multiple-choice questions independently, then share reasoning traces and revise their decisions. We conduct numerical experiments where we evaluate whether this process improves accuracy, produces more positive than negative answer transitions, and remains effective across domains such as cybersecurity, networking, and general knowledge. The results help identify when multi-agent reasoning improves reliability and when it may propagate errors. △ Less

Submitted 27 June, 2026; originally announced June 2026.

A unified deeplearning framework for contrast-phase-specific virtual monochromatic imaging

Authors: Antony Jerald, Hemant K Aggarwal, Brian Nett, Avinash Gopal, Phaneendra K Yalavarthy, Bipul Das, Rajesh Langoju

Abstract: Dual-energy CT (DECT) enables virtual monochromatic imaging (VMI) and improved contrast resolution, but its clinical adoption is limited by hardware complexity and cost. In this work, we propose a unified deep learning framework that synthesizes contrast-phase-specific virtual monochromatic 50 keV images from single-energy CT (SECT) data by leveraging contrast phase information as a prior. The mod… ▽ More Dual-energy CT (DECT) enables virtual monochromatic imaging (VMI) and improved contrast resolution, but its clinical adoption is limited by hardware complexity and cost. In this work, we propose a unified deep learning framework that synthesizes contrast-phase-specific virtual monochromatic 50 keV images from single-energy CT (SECT) data by leveraging contrast phase information as a prior. The model is trained using DECT-derived 70 keV and 50 keV image pairs across four contrast phases -- Angio, Arterial, Portal, and Delayed -- using a novel prior conditioning architecture that integrates contrast phase priors into the energy transformation process. We demonstrate that the proposed unified model achieves contrast enhancement and generalizes well across contrast phases. Additionally, we show that the model can generate 50 keV-like images from SECT inputs, preserving contrast phase-specific dynamics. △ Less

Submitted 28 May, 2026; originally announced May 2026.

Journal ref: SPIE Medical Imaging 2026

Adversarial Reframing: A Framework for Targeted Generation in Language Models

Authors: Shahnewaz Karim Sakib, Swati Kar, Anindya Bijoy Das

Abstract: Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and Exploitation of Adversarial Tactics), a reasoning-driven framework that coordinates multiple LLMs in an iterative search loop to find textual jailbreak prompts. We f… ▽ More Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and Exploitation of Adversarial Tactics), a reasoning-driven framework that coordinates multiple LLMs in an iterative search loop to find textual jailbreak prompts. We formulate prompt discovery as a nonconvex optimization problem and provide an efficient solution that lowers runtime and improves attack effectiveness. Across diverse datasets and model architectures, THREAT delivers higher attack success rates with lower computational cost than prior methods. The crafted prompts were flagged as harmful in fewer than 1% of cases, compared with about 50% refusals for the corresponding unmodified prompts. These findings reveal previously undetected vulnerabilities in aligned LLMs and position THREAT as a practical tool for proactively strengthening the safety of foundation models. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Classification of Single and Mixed Partial Discharges under Switching Voltage Using an AWA-CNN Framework

Authors: Md Rafid Kaysar Shagor, Zannatul Ferdousy Mouri, Farhina Haque, Anindya Bijoy Das

Abstract: The growing use of fast-switching power electronics has made partial discharge (PD) analysis under switching-voltage excitation increasingly important, yet more challenging than under sinusoidal conditions due to activity concentrated at voltage transitions. This work presents an Amplitude-Width-Area (AWA) pattern representation for source-oriented PD analysis under switching-voltage excitation. I… ▽ More The growing use of fast-switching power electronics has made partial discharge (PD) analysis under switching-voltage excitation increasingly important, yet more challenging than under sinusoidal conditions due to activity concentrated at voltage transitions. This work presents an Amplitude-Width-Area (AWA) pattern representation for source-oriented PD analysis under switching-voltage excitation. In the proposed method, time domain PD pulses are characterized using pulse amplitude, width, and area, and mapped into a visual pattern where amplitude and area define the coordinate axes and width is encoded by color. The generated AWA patterns are used to distinguish six single and mixed PD source conditions: corona, internal, surface, corona+internal, corona+surface, and internal+surface. To evaluate the classification capability of the proposed representation, a Random Forest baseline and two Convolutional Neural Network (CNN) models, InceptionV3 and ResNet-18, are compared. The AWA patterns show distinguishable source-dependent distributions, and CNN-based classification achieves testing accuracy above 96%, compared with 73.33% for Random Forest. The results indicate that AWA patterns provide a visual representation of PD pulses suitable for multi-class PD source classification under switching-voltage excitation. △ Less

Submitted 20 May, 2026; originally announced May 2026.

LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results

Authors: Xin Li, Daoli Xu, Wei Luo, Guoqiang Xiang, Haoran Li, Chengyu Zhuang, Zhibo Chen, Jian Guan, Weiping Li, Weixia Zhang, Wei Sun, Zhihua Wang, Dandan Zhu, Chengguang Zhu, Ayush Gupta, Rachit Agarwal, Shouvik Das, Biplab Ch Das, Amartya Ghosh, Kanglong Fan, Wen Wen, Shuyan Zhai, Tianwu Zhi, Aoxiang Zhang, Jianzhao Liu , et al. (5 additional authors not shown)

Abstract: This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality as… ▽ More This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset. △ Less

Submitted 3 August, 2026; v1 submitted 13 April, 2026; originally announced April 2026.

Comments: Accepted by CVPR2026 Workshop; LoViF Challenge

Engineering Mythology: A Digital-Physical Framework for Culturally-Inspired Public Art

Authors: Jnaneshwar Das, Christopher Filkins, Rajesh Moharana, Ekadashi Barik, Bishweshwar Das, David Ayers, Christopher Skiba, Rodney Staggers Jr, Mark Dill, Swig Miller, Daniel Tulberg, Patrick Smith, Seth Brink, Kyle Breen, Harish Anand, Ramon Arrowsmith

Abstract: Navagunjara Reborn: The Phoenix of Odisha was built for Burning Man 2025 as both a sculpture and an experiment-a fusion of myth, craft, and computation. This paper describes the digital-physical workflow developed for the project: a pipeline that linked digital sculpting, distributed fabrication by artisans in Odisha (India), modular structural optimization in the U.S., iterative feedback through… ▽ More Navagunjara Reborn: The Phoenix of Odisha was built for Burning Man 2025 as both a sculpture and an experiment-a fusion of myth, craft, and computation. This paper describes the digital-physical workflow developed for the project: a pipeline that linked digital sculpting, distributed fabrication by artisans in Odisha (India), modular structural optimization in the U.S., iterative feedback through photogrammetry and digital twins, and finally, one-shot full assembly at the art site in Black Rock Desert, Nevada. The desert installation tested not just materials, but also systems of collaboration: between artisans and engineers, between myth and technology, between cultural specificity and global experimentation. We share the lessons learned in design, fabrication, and deployment and offer a framework for future interdisciplinary projects at the intersection of cultural heritage, STEAM education, and public art. In retrospect, this workflow can be read as a convergence of many knowledge systems-artisan practice, structural engineering, mythic narrative, and environmental constraint-rather than as execution of a single fixed blueprint. △ Less

Submitted 29 March, 2026; originally announced March 2026.

Comments: 19 pages, 28 figures, 4 tables

ACM Class: I.3.5; I.3.8; I.4.1; J.5; J.2

SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense

Authors: Bibek Das, Chandranath Adak, Soumi Chattopadhyay, Zahid Akhtar, Soumya Dutta

Abstract: Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity, and public trust. Existing detection methods are largely reactive, attempting to identify manipulations after they occur and often failing to generalize across evolving generation techniques. This motivates the need for proactive mechanisms that secure media authenticity at the time of… ▽ More Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity, and public trust. Existing detection methods are largely reactive, attempting to identify manipulations after they occur and often failing to generalize across evolving generation techniques. This motivates the need for proactive mechanisms that secure media authenticity at the time of creation. In this work, we introduce SAiW, a Source-Attributed Invisible watermarking Framework for proactive deepfake defense and media provenance verification. Unlike conventional watermarking methods that treat watermark payloads as generic signals, SAiW formulates watermark embedding as a source-conditioned representation learning problem, where watermark identity encodes the originating source and modulates the embedding process to produce discriminative and traceable signatures. The framework integrates feature-wise linear modulation to inject source identity into the embedding network, enabling scalable multi-source watermark generation. A perceptual guidance module derived from human visual system priors ensures that watermark perturbations remain visually imperceptible while maintaining robustness. In addition, a dual-purpose forensic decoder simultaneously reconstructs the embedded watermark and performs source attribution, providing both automated verification and interpretable forensic evidence. Extensive experiments across multiple deepfake datasets demonstrate that SAiW achieves high perceptual quality while maintaining strong robustness against compression, filtering, noise, geometric transformations, and adversarial perturbations. By binding digital media to its origin through invisible yet verifiable markers, SAiW enables reliable authentication and source attribution, providing a scalable foundation for proactive deepfake defense and trustworthy media provenance. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering

Authors: Zhan Gao, Bishwadeep Das, Elvin Isufi

Abstract: Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolution and uncertainty into account. Existing approaches rely on either pre-designed filters or online le… ▽ More Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolution and uncertainty into account. Existing approaches rely on either pre-designed filters or online learning, limited to a myopic view considering only past or present information. To account for future impacts, we propose a stochastic sequential decision-making framework for filtering networked data with a policy that adapts filtering to expanding graphs. By representing filter shifts as agents, we model the filter as a multi-agent system and train the policy following multi-agent reinforcement learning. This accounts for long-term rewards and captures expansion dynamics through sequential decision-making. Moreover, we develop a context-aware graph neural network to parameterize the policy, which tunes filter parameters based on information of both the graph and agents. Experiments on synthetic and real datasets from cold-start recommendation to COVID prediction highlight the benefits of using a sequential decision-making perspective over batch and online filtering alternatives. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing

Authors: Fanis Mathioulakis, Gorjan Radevski, Silke GC Cleuren, Michel Janssens, Brecht Das, Koen Schauwaert, Tinne Tuytelaars

Abstract: Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stages of the printing pipeline, this task still relies heavily on manual inspection, as the set of objects to be classified can change daily, making frequent model retraining impractical. Automating the identification step… ▽ More Reliable classification of 3D-printed objects is essential for automating post-production workflows in industrial additive manufacturing. Despite extensive automation in other stages of the printing pipeline, this task still relies heavily on manual inspection, as the set of objects to be classified can change daily, making frequent model retraining impractical. Automating the identification step is therefore critical for improving operational efficiency. A vision model that could classify any set of objects by utilizing their corresponding CAD models and avoiding retraining would be highly beneficial in this setting. To enable systematic evaluation of vision models on this task, we introduce ThingiPrint, a new publicly available dataset that pairs CAD models with real photographs of their 3D-printed counterparts. Using ThingiPrint, we benchmark a range of existing vision models on the task of 3D-printed object classification. We additionally show that contrastive fine-tuning with a rotation-invariant objective allows effective prototype-based classification of previously unseen 3D-printed objects. By relying solely on the available CAD models, this avoids the need for retraining when new objects are introduced. Experiments show that this approach outperforms standard pretrained baselines, suggesting improved generalization and practical relevance for real-world use. △ Less

Submitted 8 March, 2026; originally announced March 2026.

Min-Sum Uniform Coverage Problem by Autonomous Mobile Robots

Authors: Animesh Maiti, Abhinav Chakraborty, Bibhuti Das, Subhash Bhagat, Krishnendu Mukhopadhyaya

Abstract: We study the \textit{min-sum uniform coverage} problem for a swarm of $n$ mobile robots on a given finite line segment and on a circle having finite positive radius, where the circle is given as an input. The robots must coordinate their movements to reach a uniformly spaced configuration that minimizes the total distance traveled by all robots. The robots are autonomous, anonymous, identical, and… ▽ More We study the \textit{min-sum uniform coverage} problem for a swarm of $n$ mobile robots on a given finite line segment and on a circle having finite positive radius, where the circle is given as an input. The robots must coordinate their movements to reach a uniformly spaced configuration that minimizes the total distance traveled by all robots. The robots are autonomous, anonymous, identical, and homogeneous, and operate under the \textit{Look-Compute-Move} (LCM) model with \textit{non-rigid} motion controlled by a fair asynchronous scheduler. They are oblivious and silent, possessing neither persistent memory nor a means of explicit communication. In the \textbf{line-segment setting}, the \textit{min-sum uniform coverage} problem requires placing the robots at uniformly spaced points along the segment so as to minimize the total distance traveled by all robots. In the \textbf{circle setting} for this problem, the robots have to arrange themselves uniformly around the given circle to form a regular $n$-gon. There is no fixed orientation or designated starting vertex, and the goal is to minimize the total distance traveled by all the robots. We present a deterministic distributed algorithm that achieves uniform coverage in the line-segment setting with minimum total movement cost. For the circle setting, we characterize all initial configurations for which the \textit{min-sum uniform coverage} problem is deterministically unsolvable under the considered robot model. For all the other remaining configurations, we provide a deterministic distributed algorithm that achieves uniform coverage while minimizing the total distance traveled. These results characterize the deterministic solvability of min-sum coverage for oblivious robots and achieve optimal cost whenever solvable. △ Less

Submitted 11 February, 2026; originally announced February 2026.

On Patterns and Languages in 1-11-Representations of Graphs

Authors: Biswajit Das, Ramesh Hariharasubramanian

Abstract: A 1-11-representation of a graph $G(V,E)$ is a word over the alphabet $V$ such that two distinct vertices $x$ and $y$ are adjacent if and only if the restricted word $w{x,y}$ (obtained from $w$ by deleting all letters except $x$ and $y$) contains at most one occurrence of $xx$ or $yy$. Although every graph admits a 1-11-representation, the repetition patterns that may or must appear in such repres… ▽ More A 1-11-representation of a graph $G(V,E)$ is a word over the alphabet $V$ such that two distinct vertices $x$ and $y$ are adjacent if and only if the restricted word $w{x,y}$ (obtained from $w$ by deleting all letters except $x$ and $y$) contains at most one occurrence of $xx$ or $yy$. Although every graph admits a 1-11-representation, the repetition patterns that may or must appear in such representations have not been fully studied. In this paper, we study cube-free and square-free 1-11-representations of graphs. We first show that cubes cannot always be avoided in 1-11-representations of minimum length by providing a graph for which every minimum-length 1-11-representation necessarily contains a cube. We then focus on permutational 1-11-representations, where the representing word is a concatenation of permutations of the vertex set. In this setting, we prove that any cube appearing in a permutational 1-11-representation can be removed without changing the represented graph. As a consequence, every permutational 1-11-representation attaining the permutational 1-11-representation number is cube-free. We further show that this behaviour does not extend to squares by providing a graph for which every permutational 1-11-representation with the minimum number of permutations necessarily contains a square. Finally, we prove that the language of all 1-11-representations of a given graph is regular. Moreover, we show that the language of all permutational 1-11-representations of a graph is also regular. △ Less

Submitted 28 January, 2026; originally announced January 2026.

Supervised Spike Agreement Dependent Plasticity for Fast Local Learning in Spiking Neural Networks

Authors: Gouri Lakshmi S, Athira Chandrasekharan, Harshit Kumar, Muhammed Sahad E, Bikas C Das, Saptarshi Bej

Abstract: Spike-Timing-Dependent Plasticity (STDP) provides a biologically grounded learning rule for spiking neural networks (SNNs), but its reliance on precise spike timing and pairwise updates limits fast learning of weights. We introduce a supervised extension of Spike Agreement-Dependent Plasticity (SADP), which replaces pairwise spike-timing comparisons with population-level agreement metrics such as… ▽ More Spike-Timing-Dependent Plasticity (STDP) provides a biologically grounded learning rule for spiking neural networks (SNNs), but its reliance on precise spike timing and pairwise updates limits fast learning of weights. We introduce a supervised extension of Spike Agreement-Dependent Plasticity (SADP), which replaces pairwise spike-timing comparisons with population-level agreement metrics such as Cohen's kappa. The proposed learning rule preserves strict synaptic locality, admits linear-time complexity, and enables efficient supervised learning without backpropagation, surrogate gradients, or teacher forcing. We integrate supervised SADP within hybrid CNN-SNN architectures, where convolutional encoders provide compact feature representations that are converted into Poisson spike trains for agreement-driven learning in the SNN. Extensive experiments on MNIST, Fashion-MNIST, CIFAR-10, and biomedical image classification tasks demonstrate competitive performance and fast convergence. Additional analyses show stable performance across broad hyperparameter ranges and compatibility with device-inspired synaptic update dynamics. Together, these results establish supervised SADP as a scalable, biologically grounded, and hardware-aligned learning paradigm for spiking neural networks. △ Less

Submitted 13 January, 2026; originally announced January 2026.

Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models

Authors: Badhan Chandra Das, Md Tasnim Jawad, Joaquin Molto, M. Hadi Amini, Yanzhao Wu

Abstract: In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing multi-modal tasks with high accuracy, are also severely susceptible to carefully launched security attacks, such as jailbreaking attacks, which can manipulate model… ▽ More In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing multi-modal tasks with high accuracy, are also severely susceptible to carefully launched security attacks, such as jailbreaking attacks, which can manipulate model behavior and bypass safety constraints. This paper introduces MJAD-MLLMs, a holistic framework that systematically analyzes the proposed Multi-turn Jailbreaking Attacks and multi-LLM-based defense techniques for MLLMs. In this paper, we make three original contributions. First, we introduce a novel multi-turn jailbreaking attack to exploit the vulnerabilities of the MLLMs under multi-turn prompting. Second, we propose a novel fragment-optimized and multi-LLM defense mechanism, called FragGuard, to effectively mitigate jailbreaking attacks in the MLLMs. Third, we evaluate the efficacy of the proposed attacks and defenses through extensive experiments on several state-of-the-art (SOTA) open-source and closed-source MLLMs and benchmark datasets, and compare their performance with the existing techniques. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Optimal non-adaptive algorithm for edge estimation

Authors: Arijit Bishnu, Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Gopinath Mishra

Abstract: We present a simple nonadaptive randomized algorithm that estimates the number of edges in a simple, unweighted, undirected graph, possibly containing isolated vertices, using only degree and random edge queries. For an $n$-vertex graph, our method requires only $\widetilde{O}(\sqrt{n})$ queries, achieving sublinear query complexity. The algorithm independently samples a set of vertices and querie… ▽ More We present a simple nonadaptive randomized algorithm that estimates the number of edges in a simple, unweighted, undirected graph, possibly containing isolated vertices, using only degree and random edge queries. For an $n$-vertex graph, our method requires only $\widetilde{O}(\sqrt{n})$ queries, achieving sublinear query complexity. The algorithm independently samples a set of vertices and queries their degrees, and also independently samples a set of edges, using the answers to these queries to estimate the total number of edges in the graph. We further prove a matching lower bound, establishing the optimality of our algorithm and resolving the non-adaptive query complexity of this problem with respect to degree and random-edge queries. △ Less

Submitted 12 December, 2025; originally announced December 2025.

Comments: 15 pages

MSC Class: 68W20; 68Q25; 60C05 ACM Class: F.2.2

Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction

Authors: Sithumi Wickramasinghe, Bikramjit Das, Dorien Herremans

Abstract: Bitcoin mining hardware acquisition requires strategic timing due to volatile markets, rapid technological obsolescence, and protocol-driven revenue cycles. Despite mining's evolution into a capital-intensive industry, there is little guidance on when to purchase new Application-Specific Integrated Circuit (ASIC) hardware, and no prior computational frameworks address this decision problem. We add… ▽ More Bitcoin mining hardware acquisition requires strategic timing due to volatile markets, rapid technological obsolescence, and protocol-driven revenue cycles. Despite mining's evolution into a capital-intensive industry, there is little guidance on when to purchase new Application-Specific Integrated Circuit (ASIC) hardware, and no prior computational frameworks address this decision problem. We address this gap by formulating hardware acquisition as a time series classification task, predicting whether purchasing ASIC machines yields profitable (Return on Investment (ROI) >= 1), marginal (0 < ROI < 1), or unprofitable (ROI <= 0) returns within one year. We propose MineROI-Net, an open-source Transformer-based architecture designed to capture multi-scale temporal patterns in mining profitability. Evaluated on data from 20 ASIC miners released between 2015 and 2024 across diverse market regimes, MineROI-Net outperforms recurrent, convolutional, and attention-based baselines, achieving 83.2% accuracy and 83.5% macro F1-score. The model demonstrates strong economic relevance, achieving 97.8% precision in detecting unprofitable periods and 81.5% precision in detecting profitable ones, while avoiding misclassifying profitable scenarios as unprofitable and vice versa. These results indicate that MineROI-Net offers a practical, data-driven tool for timing mining hardware acquisitions, potentially reducing financial risk in capital-intensive mining operations. △ Less

Submitted 25 May, 2026; v1 submitted 4 December, 2025; originally announced December 2025.

DS-Span: Single-Phase Discriminative Subgraph Mining for Efficient Graph Embeddings

Authors: Yeamin Kaiser, Muhammed Tasnim Bin Anwar, Bholanath Das

Abstract: Graph representation learning seeks to transform complex, high-dimensional graph structures into compact vector spaces that preserve both topology and semantics. Among the various strategies, subgraph-based methods provide an interpretable bridge between symbolic pattern discovery and continuous embedding learning. Yet, existing frequent or discriminative subgraph mining approaches often suffer fr… ▽ More Graph representation learning seeks to transform complex, high-dimensional graph structures into compact vector spaces that preserve both topology and semantics. Among the various strategies, subgraph-based methods provide an interpretable bridge between symbolic pattern discovery and continuous embedding learning. Yet, existing frequent or discriminative subgraph mining approaches often suffer from redundant multi-phase pipelines, high computational cost, and weak coupling between mined structures and their discriminative relevance. We propose DS-Span, a single-phase discriminative subgraph mining framework that unifies pattern growth, pruning, and supervision-driven scoring within one traversal of the search space. DS-Span introduces a coverage-capped eligibility mechanism that dynamically limits exploration once a graph is sufficiently represented, and an information-gain-guided selection that promotes subgraphs with strong class-separating ability while minimizing redundancy. The resulting subgraph set serves as an efficient, interpretable basis for downstream graph embedding and classification. Extensive experiments across benchmarks demonstrate that DS-Span generates more compact and discriminative subgraph features than prior multi-stage methods, achieving higher or comparable accuracy with significantly reduced runtime. These results highlight the potential of unified, single-phase discriminative mining as a foundation for scalable and interpretable graph representation learning. △ Less

Submitted 3 December, 2025; v1 submitted 21 November, 2025; originally announced November 2025.

Jailbreaking Large Vision Language Models in Intelligent Transportation Systems

Authors: Badhan Chandra Das, Md Tasnim Jawad, Md Jueal Mia, M. Hadi Amini, Yanzhao Wu

Abstract: Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper systematically analyzes the vulnerabilities of LVLMs integrated in Intelligent Transportation Systems (ITS) under carefully crafted jailbreaking attacks. First, we c… ▽ More Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper systematically analyzes the vulnerabilities of LVLMs integrated in Intelligent Transportation Systems (ITS) under carefully crafted jailbreaking attacks. First, we carefully construct a dataset with harmful queries relevant to transportation, following OpenAI's prohibited categories to which the LVLMs should not respond. Second, we introduce a novel jailbreaking attack that exploits the vulnerabilities of LVLMs through image typography manipulation and multi-turn prompting. Third, we propose a multi-layered response filtering defense technique to prevent the model from generating inappropriate responses. We perform extensive experiments with the proposed attack and defense on the state-of-the-art LVLMs (both open-source and closed-source). To evaluate the attack method and defense technique, we use GPT-4's judgment to determine the toxicity score of the generated responses, as well as manual verification. Further, we compare our proposed jailbreaking method with existing jailbreaking techniques and highlight severe security risks involved with jailbreaking attacks with image typography manipulation and multi-turn prompting in the LVLMs integrated in ITS. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Word-Representable Co-Bipartite Graphs: Vertex Ordering, Representation Number, Speed, and Entropy

Authors: Biswajit Das, Ramesh Hariharasubramanian

Abstract: A graph $G(V, E)$ is word-representable if there exists a word $w$ over the alphabet $V$ such that for distinct letters $x,y\in V$, $x$ and $y$ alternate in $w$ if and only if they are adjacent in $G$. In general, determining whether a graph is word-representable is an NP-complete problem. A graph is co-bipartite if its complement is bipartite. Therefore, the vertex set of a co-bipartite graph can… ▽ More A graph $G(V, E)$ is word-representable if there exists a word $w$ over the alphabet $V$ such that for distinct letters $x,y\in V$, $x$ and $y$ alternate in $w$ if and only if they are adjacent in $G$. In general, determining whether a graph is word-representable is an NP-complete problem. A graph is co-bipartite if its complement is bipartite. Therefore, the vertex set of a co-bipartite graph can be partitioned into two disjoint subsets $X$ and $Y$ such that the subgraphs induced by $X$ and $Y$ are cliques. In this paper, we obtain necessary and sufficient conditions for a co-bipartite graph to be word-representable in terms of a vertex ordering. Based on this ordering, we study the representation number of word-representable co-bipartite graphs and analyse the speed and entropy of this graph class. We show that the representation number of any word-representable co-bipartite graph is at most $3$, and that permutation graphs are the only co-bipartite graphs with representation number $2$. We prove that the speed is $2^{O(n \log n)}$ and the entropy is $0$. This provides an asymptotic bound on the number of labelled graphs in this class, which is significantly smaller than the known bound for the class of all co-bipartite graphs. These results provide a better understanding of the structure and enumeration of word-representable co-bipartite graphs and show that vertex ordering is an effective tool for studying this class. △ Less

Submitted 2 June, 2026; v1 submitted 3 September, 2025; originally announced September 2025.

Dimension Agnostic Testing of Survey Data Credibility through the Lens of Regression

Authors: Debabrota Basu, Sourav Chakraborty, Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Arnab Ray

Abstract: Assessing whether a sample survey credibly represents the population is a critical question for ensuring the validity of downstream research. Generally, this problem reduces to estimating the distance between two high-dimensional distributions, which typically requires a number of samples that grows exponentially with the dimension. However, depending on the model used for data analysis, the concl… ▽ More Assessing whether a sample survey credibly represents the population is a critical question for ensuring the validity of downstream research. Generally, this problem reduces to estimating the distance between two high-dimensional distributions, which typically requires a number of samples that grows exponentially with the dimension. However, depending on the model used for data analysis, the conclusions drawn from the data may remain consistent across different underlying distributions. In this context, we propose a task-based approach to assess the credibility of sampled surveys. Specifically, we introduce a model-specific distance metric to quantify this notion of credibility. We also design an algorithm to verify the credibility of survey data in the context of regression models. Notably, the sample complexity of our algorithm is independent of the data dimension. This efficiency stems from the fact that the algorithm focuses on verifying the credibility of the survey data rather than reconstructing the underlying regression model. Furthermore, we show that if one attempts to verify credibility by reconstructing the regression model, the sample complexity scales linearly with the dimensionality of the data. We prove the theoretical correctness of our algorithm and numerically demonstrate our algorithm's performance. △ Less

Submitted 28 August, 2025; originally announced August 2025.

Comments: 30 pages, 8 figures, 6 Tables

Rethinking Federated Learning Over the Air: The Blessing of Scaling Up

Authors: Jiaqi Zhu, Bikramjit Das, Yong Xie, Nikolaos Pappas, Howard H. Yang

Abstract: Federated learning facilitates collaborative model training across multiple clients while preserving data privacy. However, its performance is often constrained by limited communication resources, particularly in systems supporting a large number of clients. To address this challenge, integrating over-the-air computations into the training process has emerged as a promising solution to alleviate c… ▽ More Federated learning facilitates collaborative model training across multiple clients while preserving data privacy. However, its performance is often constrained by limited communication resources, particularly in systems supporting a large number of clients. To address this challenge, integrating over-the-air computations into the training process has emerged as a promising solution to alleviate communication bottlenecks. The system significantly increases the number of clients it can support in each communication round by transmitting intermediate parameters via analog signals rather than digital ones. This improvement, however, comes at the cost of channel-induced distortions, such as fading and noise, which affect the aggregated global parameters. To elucidate these effects, this paper develops a theoretical framework to analyze the performance of over-the-air federated learning in large-scale client scenarios. Our analysis reveals three key advantages of scaling up the number of participating clients: (1) Enhanced Privacy: The mutual information between a client's local gradient and the server's aggregated gradient diminishes, effectively reducing privacy leakage. (2) Mitigation of Channel Fading: The channel hardening effect eliminates the impact of small-scale fading in the noisy global gradient. (3) Improved Convergence: Reduced thermal noise and gradient estimation errors benefit the convergence rate. These findings solidify over-the-air model training as a viable approach for federated learning in networks with a large number of clients. The theoretical insights are further substantiated through extensive experimental evaluations. △ Less

Submitted 25 August, 2025; originally announced August 2025.

Quickly Tuning Foundation Models for Image Segmentation

Authors: Breenda Das, Lennart Purucker, Timur Carstensen, Frank Hutter

Abstract: Foundation models like SAM (Segment Anything Model) exhibit strong zero-shot image segmentation performance, but often fall short on domain-specific tasks. Fine-tuning these models typically requires significant manual effort and domain expertise. In this work, we introduce QTT-SEG, a meta-learning-driven approach for automating and accelerating the fine-tuning of SAM for image segmentation. Built… ▽ More Foundation models like SAM (Segment Anything Model) exhibit strong zero-shot image segmentation performance, but often fall short on domain-specific tasks. Fine-tuning these models typically requires significant manual effort and domain expertise. In this work, we introduce QTT-SEG, a meta-learning-driven approach for automating and accelerating the fine-tuning of SAM for image segmentation. Built on the Quick-Tune hyperparameter optimization framework, QTT-SEG predicts high-performing configurations using meta-learned cost and performance models, efficiently navigating a search space of over 200 million possibilities. We evaluate QTT-SEG on eight binary and five multiclass segmentation datasets under tight time constraints. Our results show that QTT-SEG consistently improves upon SAM's zero-shot performance and surpasses AutoGluon Multimodal, a strong AutoML baseline, on most binary tasks within three minutes. On multiclass datasets, QTT-SEG delivers consistent gains as well. These findings highlight the promise of meta-learning in automating model adaptation for specialized segmentation tasks. Code available at: https://github.com/ds-brx/QTT-SEG/ △ Less

Submitted 24 August, 2025; originally announced August 2025.

Comments: Accepted as a short paper at the non-archival content track of AutoML 2025

Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks

Authors: Saptarshi Bej, Muhammed Sahad E, Gouri Lakshmi, Harshit Kumar, Pritam Kar, Bikas C Das

Abstract: We introduce Spike Agreement Dependent Plasticity (SADP), a biologically inspired synaptic learning rule for Spiking Neural Networks (SNNs) that relies on the agreement between pre- and post-synaptic spike trains rather than precise spike-pair timing. SADP generalizes classical Spike-Timing-Dependent Plasticity (STDP) by replacing pairwise temporal updates with population-level correlation metrics… ▽ More We introduce Spike Agreement Dependent Plasticity (SADP), a biologically inspired synaptic learning rule for Spiking Neural Networks (SNNs) that relies on the agreement between pre- and post-synaptic spike trains rather than precise spike-pair timing. SADP generalizes classical Spike-Timing-Dependent Plasticity (STDP) by replacing pairwise temporal updates with population-level correlation metrics such as Cohen's kappa. The SADP update rule admits linear-time complexity and supports efficient hardware implementation via bitwise logic. Empirical results on MNIST and Fashion-MNIST show that SADP, especially when equipped with spline-based kernels derived from our experimental iontronic organic memtransistor device data, outperforms classical STDP in both accuracy and runtime. Our framework bridges the gap between biological plausibility and computational scalability, offering a viable learning mechanism for neuromorphic systems. △ Less

Submitted 22 August, 2025; originally announced August 2025.

Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities

Authors: Anindya Bijoy Das, Shahnewaz Karim Sakib, Shibbir Ahmed

Abstract: Large Language Models (LLMs) are increasingly applied to medical imaging tasks, including image interpretation and synthetic image generation. However, these models often produce hallucinations, which are confident but incorrect outputs that can mislead clinical decisions. This study examines hallucinations in two directions: image to text, where LLMs generate reports from X-ray, CT, or MRI scans,… ▽ More Large Language Models (LLMs) are increasingly applied to medical imaging tasks, including image interpretation and synthetic image generation. However, these models often produce hallucinations, which are confident but incorrect outputs that can mislead clinical decisions. This study examines hallucinations in two directions: image to text, where LLMs generate reports from X-ray, CT, or MRI scans, and text to image, where models create medical images from clinical prompts. We analyze errors such as factual inconsistencies and anatomical inaccuracies, evaluating outputs using expert informed criteria across imaging modalities. Our findings reveal common patterns of hallucination in both interpretive and generative tasks, with implications for clinical reliability. We also discuss factors contributing to these failures, including model architecture and training data. By systematically studying both image understanding and generation, this work provides insights into improving the safety and trustworthiness of LLM driven medical imaging systems. △ Less

Submitted 9 August, 2025; originally announced August 2025.

AI-Driven Cybersecurity Threat Detection: Building Resilient Defense Systems Using Predictive Analytics

Authors: Biswajit Chandra Das, M Saif Sartaz, Syed Ali Reza, Arat Hossain, Md Nasiruddin, Kanchon Kumar Bishnu, Kazi Sharmin Sultana, Sadia Sharmeen Shatyi, MD Azam Khan, Joynal Abed

Abstract: This study examines how Artificial Intelligence can aid in identifying and mitigating cyber threats in the U.S. across four key areas: intrusion detection, malware classification, phishing detection, and insider threat analysis. Each of these problems has its quirks, meaning there needs to be different approaches to each, so we matched the models to the shape of the problem. For intrusion detectio… ▽ More This study examines how Artificial Intelligence can aid in identifying and mitigating cyber threats in the U.S. across four key areas: intrusion detection, malware classification, phishing detection, and insider threat analysis. Each of these problems has its quirks, meaning there needs to be different approaches to each, so we matched the models to the shape of the problem. For intrusion detection, catching things like unauthorized access, we tested unsupervised anomaly detection methods. Isolation forests and deep autoencoders both gave us useful signals by picking up odd patterns in network traffic. When it came to malware detection, we leaned on ensemble models like Random Forest and XGBoost, trained on features pulled from files and traffic logs. Phishing was more straightforward. We fed standard classifiers (logistic regression, Random Forest, XGBoost) a mix of email and web-based features. These models handled the task surprisingly well. Phishing turned out to be the easiest problem to crack, at least with the data we had. There was a different story. We utilized an LSTM autoencoder to identify behavioral anomalies in user activity logs. It caught every suspicious behavior but flagged a lot of harmless ones too. That kind of model makes sense when the cost of missing a threat is high and you are willing to sift through some noise. What we saw across the board is that performance was not about stacking the most complex model. What mattered was how well the models structure matched the way the data behaved. When signals were strong and obvious, simple models worked fine. But for messier, more subtle threats, we needed something more adaptive, sequence models and anomaly detectors, though they brought their trade offs. The takeaway here is clear in cybersecurity, context drives the solution. △ Less

Submitted 2 August, 2025; originally announced August 2025.

Towards Benchmarking Foundation Models for Tabular Data With Text

Authors: Martin Mráz, Breenda Das, Anshul Gupta, Lennart Purucker, Frank Hutter

Abstract: Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strat… ▽ More Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strategies for incorporating text into conventional tabular pipelines. Moreover, we benchmark how state-of-the-art tabular foundation models can handle textual data by manually curating a collection of real-world tabular datasets with meaningful textual features. Our study is an important step towards improving benchmarking of foundation models for tabular data with text. △ Less

Submitted 10 July, 2025; originally announced July 2025.

Comments: Accepted at Foundation Models for Structured Data workshop at ICML 2025

On the Complexity of Problems on Graphs Defined on Groups

Authors: Bireswar Das, Dipan Dey, Jinia Ghosh

Abstract: We study the complexity of graph problems on graphs defined on groups, especially power graphs. We observe that an isomorphism invariant problem, such as Hamiltonian Path, Partition into Cliques, Feedback Vertex Set, Subgraph Isomorphism, cannot be NP-complete for power graphs, commuting graphs, enhanced power graphs, directed power graphs, and bounded-degree Cayley graphs, assuming the Exponentia… ▽ More We study the complexity of graph problems on graphs defined on groups, especially power graphs. We observe that an isomorphism invariant problem, such as Hamiltonian Path, Partition into Cliques, Feedback Vertex Set, Subgraph Isomorphism, cannot be NP-complete for power graphs, commuting graphs, enhanced power graphs, directed power graphs, and bounded-degree Cayley graphs, assuming the Exponential Time Hypothesis (ETH). An analogous result holds for isomorphism invariant group problems: no such problem can be NP-complete unless ETH is false. We show that the Weighted Max-Cut problem is NP-complete in power graphs. We also show that, unless ETH is false, the Graph Motif problem cannot be solved in quasipolynomial time on power graphs, even for power graphs of cyclic groups. We study the recognition problem of power graphs when the adjacency matrix or list is given as input and show that for abelian groups and some classes of nilpotent groups, it is solvable in polynomial time. △ Less

Submitted 8 July, 2025; originally announced July 2025.

Comments: 22 pages, this is the full version of the corresponding paper accepted at the 25th International Symposium on Fundamentals of Computation Theory (FCT 2025)

ACM Class: F.1.3; G.2.2

Graph signal aware decomposition of dynamic networks via latent graphs

Authors: Bishwadeep Das, Andrei Buciulea, Antonio G. Marques, Elvin Isufi

Abstract: Dynamics on and of networks refer to changes in topology and node-associated signals, respectively and are pervasive in many socio-technological systems, including social, biological, and infrastructure networks. Due to practical constraints, privacy concerns, or malfunctions, we often observe only a fraction of the topological evolution and associated signal, which not only hinders downstream tas… ▽ More Dynamics on and of networks refer to changes in topology and node-associated signals, respectively and are pervasive in many socio-technological systems, including social, biological, and infrastructure networks. Due to practical constraints, privacy concerns, or malfunctions, we often observe only a fraction of the topological evolution and associated signal, which not only hinders downstream tasks but also restricts our analysis of network evolution. Such aspects could be mitigated by moving our attention at the underlying latent driving factors of the network evolution, which can be naturally uncovered via low-rank tensor decomposition. Tensor-based methods provide a powerful means of uncovering the underlying factors of network evolution through low-rank decompositions. However, the extracted embeddings typically lack a relational structure and are obtained independently from the node signals. This disconnect reduces the interpretability of the embeddings and overlooks the coupling between topology and signals. To address these limitations, we propose a novel two-way decomposition to represent a dynamic graph topology, where the structural evolution is captured by a linear combination of latent graph adjacency matrices reflecting the overall joint evolution of both the topology and the signal. Using spatio-temporal data, we estimate the latent adjacency matrices and their temporal scaling signatures via alternating minimization, and prove that our approach converges to a stationary point. Numerical results show that the proposed method recovers individually and collectively expressive latent graphs, outperforming both standard tensor-based decompositions and signal-based topology identification methods in reconstructing the missing network especially when observations are limited. △ Less

Submitted 10 June, 2025; originally announced June 2025.

Comments: 13 Pages, 9 Figures

System Prompt Extraction Attacks and Defenses in Large Language Models

Authors: Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu

Abstract: The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries… ▽ More The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries, raising significant privacy and security concerns. Despite the growing threat, there is a lack of systematic studies of system prompt extraction attacks and defenses. In this paper, we present a comprehensive framework, SPE-LLM, to systematically evaluate System Prompt Extraction attacks and defenses in LLMs. First, we design a set of novel adversarial queries that effectively extract system prompts in state-of-the-art (SOTA) LLMs, demonstrating the severe risks of LLM system prompt extraction attacks. Second, we propose three defense techniques to mitigate system prompt extraction attacks in LLMs, providing practical solutions for secure LLM deployments. Third, we introduce a set of rigorous evaluation metrics to accurately quantify the severity of system prompt extraction attacks in LLMs and conduct comprehensive experiments across multiple benchmark datasets, which validates the efficacy of our proposed SPE-LLM framework. △ Less

Submitted 27 May, 2025; originally announced May 2025.

Can Large Language Models Challenge CNNs in Medical Image Analysis?

Authors: Shibbir Ahmed, Shahnewaz Karim Sakib, Anindya Bijoy Das

Abstract: This study presents a multimodal AI framework designed for precisely classifying medical diagnostic images. Utilizing publicly available datasets, the proposed system compares the strengths of convolutional neural networks (CNNs) and different large language models (LLMs). This in-depth comparative analysis highlights key differences in diagnostic performance, execution efficiency, and environment… ▽ More This study presents a multimodal AI framework designed for precisely classifying medical diagnostic images. Utilizing publicly available datasets, the proposed system compares the strengths of convolutional neural networks (CNNs) and different large language models (LLMs). This in-depth comparative analysis highlights key differences in diagnostic performance, execution efficiency, and environmental impacts. Model evaluation was based on accuracy, F1-score, average execution time, average energy consumption, and estimated $CO_2$ emission. The findings indicate that although CNN-based models can outperform various multimodal techniques that incorporate both images and contextual information, applying additional filtering on top of LLMs can lead to substantial performance gains. These findings highlight the transformative potential of multimodal AI systems to enhance the reliability, efficiency, and scalability of medical diagnostics in clinical settings. △ Less

Submitted 3 June, 2025; v1 submitted 29 May, 2025; originally announced May 2025.

Comparative analysis of subword tokenization approaches for Indian languages

Authors: Sudhansu Bala Das, Samujjal Choudhury, Tapas Kumar Mishra, Bidyut Kr. Patra

Abstract: Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by breaking down words into smaller subword units, which is especially beneficial in languages with complicated morphology or a vast vocabulary. It is useful in capturing the intricat… ▽ More Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by breaking down words into smaller subword units, which is especially beneficial in languages with complicated morphology or a vast vocabulary. It is useful in capturing the intricate structure of words in Indian languages (ILs), such as prefixes, suffixes, and other morphological variations. These languages frequently use agglutinative structures, in which words are formed by the combination of multiple morphemes such as suffixes, prefixes, and stems. As a result, a suitable tokenization strategy must be chosen to address these scenarios. This paper examines how different subword tokenization techniques, such as SentencePiece, Byte Pair Encoding (BPE), and WordPiece Tokenization, affect ILs. The effectiveness of these subword tokenization techniques is investigated in statistical, neural, and multilingual neural machine translation models. All models are examined using standard evaluation metrics, such as the Bilingual Evaluation Understudy (BLEU) score, TER, METEOR, CHRF, RIBES, and COMET. Based on the results, it appears that for the majority of language pairs for the Statistical and Neural MT models, the SentencePiece tokenizer continuously performed better than other tokenizers in terms of BLEU score. However, BPE tokenization outperformed other tokenization techniques in the context of Multilingual Neural Machine Translation model. The results show that, despite using the same tokenizer and dataset for each model, translations from ILs to English surpassed translations from English to ILs. △ Less

Submitted 22 May, 2025; originally announced May 2025.

Comments: 24 pages, 4 tables

VIViT: Variable-Input Vision Transformer Framework for 3D MR Image Segmentation

Authors: Badhan Kumar Das, Ajay Singh, Gengyan Zhao, Han Liu, Thomas J. Re, Dorin Comaniciu, Eli Gibson, Andreas Maier

Abstract: Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition protocols, which poses challenges for the current deep learning methods on large-scale pretrain and different downstream tasks with different input requirements, since… ▽ More Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition protocols, which poses challenges for the current deep learning methods on large-scale pretrain and different downstream tasks with different input requirements, since these methods typically require a fixed set of input modalities or, contrasts. To address this challenge, we propose variable-input ViT (VIViT), a transformer-based framework designed for self-supervised pretraining and segmentation finetuning for variable contrasts in each study. With this ability, our approach can maximize the data availability in pretrain, and can transfer the learned knowledge from pretrain to downstream tasks despite variations in input requirements. We validate our method on brain infarct and brain tumor segmentation, where our method outperforms current CNN and ViT-based models with a mean Dice score of 0.624 and 0.883 respectively. These results highlight the efficacy of our design for better adaptability and performance on tasks with real-world heterogeneous MR data. △ Less

Submitted 14 June, 2025; v1 submitted 13 May, 2025; originally announced May 2025.

Comments: 9 pages

Multi-Plane Vision Transformer for Hemorrhage Classification Using Axial and Sagittal MRI Data

Authors: Badhan Kumar Das, Gengyan Zhao, Boris Mailhe, Thomas J. Re, Dorin Comaniciu, Eli Gibson, Andreas Maier

Abstract: Identifying brain hemorrhages from magnetic resonance imaging (MRI) is a critical task for healthcare professionals. The diverse nature of MRI acquisitions with varying contrasts and orientation introduce complexity in identifying hemorrhage using neural networks. For acquisitions with varying orientations, traditional methods often involve resampling images to a fixed plane, which can lead to inf… ▽ More Identifying brain hemorrhages from magnetic resonance imaging (MRI) is a critical task for healthcare professionals. The diverse nature of MRI acquisitions with varying contrasts and orientation introduce complexity in identifying hemorrhage using neural networks. For acquisitions with varying orientations, traditional methods often involve resampling images to a fixed plane, which can lead to information loss. To address this, we propose a 3D multi-plane vision transformer (MP-ViT) for hemorrhage classification with varying orientation data. It employs two separate transformer encoders for axial and sagittal contrasts, using cross-attention to integrate information across orientations. MP-ViT also includes a modality indication vector to provide missing contrast information to the model. The effectiveness of the proposed model is demonstrated with extensive experiments on real world clinical dataset consists of 10,084 training, 1,289 validation and 1,496 test subjects. MP-ViT achieved substantial improvement in area under the curve (AUC), outperforming the vision transformer (ViT) by 5.5% and CNN-based architectures by 1.8%. These results highlight the potential of MP-ViT in improving performance for hemorrhage detection when different orientation contrasts are needed. △ Less

Submitted 12 May, 2025; originally announced May 2025.

Comments: 10 pages

p-complete square-free Word-representation of Word-representable Graphs

Authors: Biswajit Das, Ramesh Hariharasubramanian

Abstract: A graph G(V, E) is word-representable if there exists a word w over V such that distinct letters x and y alternate in w iff $xy \in E$. We introduce p-complete squares and p-complete square-free word-representable graphs. A word is p-complete square-free if no induced subword over any subset of letters contains a square XX with $|X| \ge p$. A graph is p-complete square-free if it admits such a rep… ▽ More A graph G(V, E) is word-representable if there exists a word w over V such that distinct letters x and y alternate in w iff $xy \in E$. We introduce p-complete squares and p-complete square-free word-representable graphs. A word is p-complete square-free if no induced subword over any subset of letters contains a square XX with $|X| \ge p$. A graph is p-complete square-free if it admits such a representation. We define p-complete square-free uniform word-representations and study their properties. We show that any graph admitting such a representation forbids Kp as an induced subgraph and that the recognition problem is NP-hard for arbitrary p. For p=1 and 2, we give complete characterisations. We prove that every $K_p$-free circle graph admits a p-complete square-free uniform representation and that any 3-complete square-free uniform word-representable graph has representation number at most three. We present a constructive method for generating new examples for p=3. △ Less

Submitted 24 December, 2025; v1 submitted 8 May, 2025; originally announced May 2025.

Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models

Authors: Anindya Bijoy Das, Shibbir Ahmed, Shahnewaz Karim Sakib

Abstract: Clinical summarization is crucial in healthcare as it distills complex medical data into digestible information, enhancing patient understanding and care management. Large language models (LLMs) have shown significant potential in automating and improving the accuracy of such summarizations due to their advanced natural language understanding capabilities. These models are particularly applicable… ▽ More Clinical summarization is crucial in healthcare as it distills complex medical data into digestible information, enhancing patient understanding and care management. Large language models (LLMs) have shown significant potential in automating and improving the accuracy of such summarizations due to their advanced natural language understanding capabilities. These models are particularly applicable in the context of summarizing medical/clinical texts, where precise and concise information transfer is essential. In this paper, we investigate the effectiveness of open-source LLMs in extracting key events from discharge reports, including admission reasons, major in-hospital events, and critical follow-up actions. In addition, we also assess the prevalence of various types of hallucinations in the summaries produced by these models. Detecting hallucinations is vital as it directly influences the reliability of the information, potentially affecting patient care and treatment outcomes. We conduct comprehensive simulations to rigorously evaluate the performance of these models, further probing the accuracy and fidelity of the extracted content in clinical summarization. Our results reveal that while the LLMs (e.g., Qwen2.5 and DeepSeek-v2) perform quite well in capturing admission reasons and hospitalization events, they are generally less consistent when it comes to identifying follow-up recommendations, highlighting broader challenges in leveraging LLMs for comprehensive summarization. △ Less

Submitted 20 August, 2025; v1 submitted 26 April, 2025; originally announced April 2025.

Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo

Authors: Ocheme Anthony Ekle, Biswarup Das

Abstract: In this study, we develop Neural Machine Translation (NMT) and Transformer-based transfer learning models for English-to-Igbo translation - a low-resource African language spoken by over 40 million people across Nigeria and West Africa. Our models are trained on a curated and benchmarked dataset compiled from Bible corpora, local news, Wikipedia articles, and Common Crawl, all verified by native l… ▽ More In this study, we develop Neural Machine Translation (NMT) and Transformer-based transfer learning models for English-to-Igbo translation - a low-resource African language spoken by over 40 million people across Nigeria and West Africa. Our models are trained on a curated and benchmarked dataset compiled from Bible corpora, local news, Wikipedia articles, and Common Crawl, all verified by native language experts. We leverage Recurrent Neural Network (RNN) architectures, including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), enhanced with attention mechanisms to improve translation accuracy. To further enhance performance, we apply transfer learning using MarianNMT pre-trained models within the SimpleTransformers framework. Our RNN-based system achieves competitive results, closely matching existing English-Igbo benchmarks. With transfer learning, we observe a performance gain of +4.83 BLEU points, reaching an estimated translation accuracy of 70%. These findings highlight the effectiveness of combining RNNs with transfer learning to address the performance gap in low-resource language translation tasks. △ Less

Submitted 24 April, 2025; originally announced April 2025.

Comments: 25 pages, 14 combined figures (19 total), includes horizontal layouts. Submitted to arXiv for open access

MSC Class: 68T50; 68T01 ACM Class: I.2.7; I.2.1

AdaViT: Adaptive Vision Transformer for Flexible Pretrain and Finetune with Variable 3D Medical Image Modalities

Authors: Badhan Kumar Das, Gengyan Zhao, Han Liu, Thomas J. Re, Dorin Comaniciu, Eli Gibson, Andreas Maier

Abstract: Pretrain techniques, whether supervised or self-supervised, are widely used in deep learning to enhance model performance. In real-world clinical scenarios, different sets of magnetic resonance (MR) contrasts are often acquired for different subjects/cases, creating challenges for deep learning models assuming consistent input modalities among all the cases and between pretrain and finetune. Exist… ▽ More Pretrain techniques, whether supervised or self-supervised, are widely used in deep learning to enhance model performance. In real-world clinical scenarios, different sets of magnetic resonance (MR) contrasts are often acquired for different subjects/cases, creating challenges for deep learning models assuming consistent input modalities among all the cases and between pretrain and finetune. Existing methods struggle to maintain performance when there is an input modality/contrast set mismatch with the pretrained model, often resulting in degraded accuracy. We propose an adaptive Vision Transformer (AdaViT) framework capable of handling variable set of input modalities for each case. We utilize a dynamic tokenizer to encode different input image modalities to tokens and take advantage of the characteristics of the transformer to build attention mechanism across variable length of tokens. Through extensive experiments, we demonstrate that this architecture effectively transfers supervised pretrained models to new datasets with different input modality/contrast sets, resulting in superior performance on zero-shot testing, few-shot finetuning, and backward transferring in brain infarct and brain tumor segmentation tasks. Additionally, for self-supervised pretrain, the proposed method is able to maximize the pretrain data and facilitate transferring to diverse downstream tasks with variable sets of input modalities. △ Less

Submitted 4 April, 2025; originally announced April 2025.

Machine Learning-Based Detection and Analysis of Suspicious Activities in Bitcoin Wallet Transactions in the USA

Authors: Md Zahidul Islam, Md Shahidul Islam, Biswajit Chandra das, Syed Ali Reza, Proshanta Kumar Bhowmik, Kanchon Kumar Bishnu, Md Shafiqur Rahman, Redoyan Chowdhury, Laxmi Pant

Abstract: The dramatic adoption of Bitcoin and other cryptocurrencies in the USA has revolutionized the financial landscape and provided unprecedented investment and transaction efficiency opportunities. The prime objective of this research project is to develop machine learning algorithms capable of effectively identifying and tracking suspicious activity in Bitcoin wallet transactions. With high-tech anal… ▽ More The dramatic adoption of Bitcoin and other cryptocurrencies in the USA has revolutionized the financial landscape and provided unprecedented investment and transaction efficiency opportunities. The prime objective of this research project is to develop machine learning algorithms capable of effectively identifying and tracking suspicious activity in Bitcoin wallet transactions. With high-tech analysis, the study aims to create a model with a feature for identifying trends and outliers that can expose illicit activity. The current study specifically focuses on Bitcoin transaction information in America, with a strong emphasis placed on the importance of knowing about the immediate environment in and through which such transactions pass through. The dataset is composed of in-depth Bitcoin wallet transactional information, including important factors such as transaction values, timestamps, network flows, and addresses for wallets. All entries in the dataset expose information about financial transactions between wallets, including received and sent transactions, and such information is significant for analysis and trends that can represent suspicious activity. This study deployed three accredited algorithms, most notably, Logistic Regression, Random Forest, and Support Vector Machines. In retrospect, Random Forest emerged as the best model with the highest F1 Score, showcasing its ability to handle non-linear relationships in the data. Insights revealed significant patterns in wallet activity, such as the correlation between unredeemed transactions and final balances. The application of machine algorithms in tracking cryptocurrencies is a tool for creating transparent and secure U.S. markets. △ Less

Submitted 3 April, 2025; originally announced April 2025.

Comments: 20 pages,7 figures

Exploration of Hepatitis B Virus Infection Dynamics through Physics-Informed Deep Learning Approach

Authors: Bikram Das, Rupchand Sutradhar, D C Dalal

Abstract: Accurate forecasting of viral disease outbreaks is crucial for guiding public health responses and preventing widespread loss of life. In recent years, Physics-Informed Neural Networks (PINNs) have emerged as a promising framework that can capture the intricate dynamics of viral infection and reliably predict its future progression. However, despite notable advances, the application of PINNs in di… ▽ More Accurate forecasting of viral disease outbreaks is crucial for guiding public health responses and preventing widespread loss of life. In recent years, Physics-Informed Neural Networks (PINNs) have emerged as a promising framework that can capture the intricate dynamics of viral infection and reliably predict its future progression. However, despite notable advances, the application of PINNs in disease modeling remains limited. Standard PINNs are effective in simulating disease dynamics through forward modeling but often face challenges in estimating key biological parameters from sparse or noisy experimental data when applied in an inverse framework. To overcome these limitations, a recent extension known as Disease Informed Neural Networks (DINNs) has emerged, offering a more robust approach to parameter estimation tasks. In this work, we apply this DINNs technique on a recently proposed hepatitis B virus (HBV) infection dynamics model to predict infection transmission within the liver. This model consists of four compartments: uninfected and infected hepatocytes, rcDNA-containing capsids, and free viruses. Leveraging the power of DINNs, we study the impacts of (i) variations in parameter range, (ii) experimental noise in data, (iii) sample sizes, (iv) network architecture and (v) learning rate. We employ this methodology in experimental data collected from nine HBV-infected chimpanzees and observe that it reliably estimates the model parameters. DINNs can capture infection dynamics and predict their future progression even when data of some compartments of the system are missing. Additionally, it identifies the influential model parameters that determine whether the HBV infection is cleared or persists within the host. △ Less

Submitted 10 August, 2025; v1 submitted 12 March, 2025; originally announced March 2025.

Battling Misinformation: An Empirical Study on Adversarial Factuality in Open-Source Large Language Models

Authors: Shahnewaz Karim Sakib, Anindya Bijoy Das, Shibbir Ahmed

Abstract: Adversarial factuality refers to the deliberate insertion of misinformation into input prompts by an adversary, characterized by varying levels of expressed confidence. In this study, we systematically evaluate the performance of several open-source large language models (LLMs) when exposed to such adversarial inputs. Three tiers of adversarial confidence are considered: strongly confident, modera… ▽ More Adversarial factuality refers to the deliberate insertion of misinformation into input prompts by an adversary, characterized by varying levels of expressed confidence. In this study, we systematically evaluate the performance of several open-source large language models (LLMs) when exposed to such adversarial inputs. Three tiers of adversarial confidence are considered: strongly confident, moderately confident, and limited confidence. Our analysis encompasses eight LLMs: LLaMA 3.1 (8B), Phi 3 (3.8B), Qwen 2.5 (7B), Deepseek-v2 (16B), Gemma2 (9B), Falcon (7B), Mistrallite (7B), and LLaVA (7B). Empirical results indicate that LLaMA 3.1 (8B) exhibits a robust capability in detecting adversarial inputs, whereas Falcon (7B) shows comparatively lower performance. Notably, for the majority of the models, detection success improves as the adversary's confidence decreases; however, this trend is reversed for LLaMA 3.1 (8B) and Phi 3 (3.8B), where a reduction in adversarial confidence corresponds with diminished detection performance. Further analysis of the queries that elicited the highest and lowest rates of successful attacks reveals that adversarial attacks are more effective when targeting less commonly referenced or obscure information. △ Less

Submitted 11 March, 2025; originally announced March 2025.

SegResMamba: An Efficient Architecture for 3D Medical Image Segmentation

Authors: Badhan Kumar Das, Ajay Singh, Saahil Islam, Gengyan Zhao, Andreas Maier

Abstract: The Transformer architecture has opened a new paradigm in the domain of deep learning with its ability to model long-range dependencies and capture global context and has outpaced the traditional Convolution Neural Networks (CNNs) in many aspects. However, applying Transformer models to 3D medical image datasets presents significant challenges due to their high training time, and memory requiremen… ▽ More The Transformer architecture has opened a new paradigm in the domain of deep learning with its ability to model long-range dependencies and capture global context and has outpaced the traditional Convolution Neural Networks (CNNs) in many aspects. However, applying Transformer models to 3D medical image datasets presents significant challenges due to their high training time, and memory requirements, which not only hinder scalability but also contribute to elevated CO$_2$ footprint. This has led to an exploration of alternative models that can maintain or even improve performance while being more efficient and environmentally sustainable. Recent advancements in Structured State Space Models (SSMs) effectively address some of the inherent limitations of Transformers, particularly their high memory and computational demands. Inspired by these advancements, we propose an efficient 3D segmentation model for medical imaging called SegResMamba, designed to reduce computation complexity, memory usage, training time, and environmental impact while maintaining high performance. Our model uses less than half the memory during training compared to other state-of-the-art (SOTA) architectures, achieving comparable performance with significantly reduced resource demands. △ Less

Submitted 10 March, 2025; originally announced March 2025.

Accurate and Efficient Two-Stage Gun Detection in Video

Authors: Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu

Abstract: Object detection in videos plays a crucial role in advancing applications such as public safety and anomaly detection. Existing methods have explored different techniques, including CNN, deep learning, and Transformers, for object detection and video classification. However, detecting tiny objects, e.g., guns, in videos remains challenging due to their small scale and varying appearances in comple… ▽ More Object detection in videos plays a crucial role in advancing applications such as public safety and anomaly detection. Existing methods have explored different techniques, including CNN, deep learning, and Transformers, for object detection and video classification. However, detecting tiny objects, e.g., guns, in videos remains challenging due to their small scale and varying appearances in complex scenes. Moreover, existing video analysis models for classification or detection often perform poorly in real-world gun detection scenarios due to limited labeled video datasets for training. Thus, developing efficient methods for effectively capturing tiny object features and designing models capable of accurate gun detection in real-world videos is imperative. To address these challenges, we make three original contributions in this paper. First, we conduct an empirical study of several existing video classification and object detection methods to identify guns in videos. Our extensive analysis shows that these methods may not accurately detect guns in videos. Second, we propose a novel two-stage gun detection method. In stage 1, we train an image-augmented model to effectively classify ``Gun'' videos. To make the detection more precise and efficient, stage 2 employs an object detection model to locate the exact region of the gun within video frames for videos classified as ``Gun'' by stage 1. Third, our experimental results demonstrate that the proposed domain-specific method achieves significant performance improvements and enhances efficiency compared with existing techniques. We also discuss challenges and future research directions in gun detection tasks in computer vision. △ Less

Submitted 8 March, 2025; originally announced March 2025.

Display Field-Of-View Agnostic Robust CT Kernel Synthesis Using Model-Based Deep Learning

Authors: Hemant Kumar Aggarwal, Antony Jerald, Phaneendra K. Yalavarthy, Rajesh Langoju, Bipul Das

Abstract: In X-ray computed tomography (CT) imaging, the choice of reconstruction kernel is crucial as it significantly impacts the quality of clinical images. Different kernels influence spatial resolution, image noise, and contrast in various ways. Clinical applications involving lung imaging often require images reconstructed with both soft and sharp kernels. The reconstruction of images with different k… ▽ More In X-ray computed tomography (CT) imaging, the choice of reconstruction kernel is crucial as it significantly impacts the quality of clinical images. Different kernels influence spatial resolution, image noise, and contrast in various ways. Clinical applications involving lung imaging often require images reconstructed with both soft and sharp kernels. The reconstruction of images with different kernels requires raw sinogram data and storing images for all kernels increases processing time and storage requirements. The Display Field-of-View (DFOV) adds complexity to kernel synthesis, as data acquired at different DFOVs exhibit varying levels of sharpness and details. This work introduces an efficient, DFOV-agnostic solution for image-based kernel synthesis using model-based deep learning. The proposed method explicitly integrates CT kernel and DFOV characteristics into the forward model. Experimental results on clinical data, along with quantitative analysis of the estimated modulation transfer function using wire phantom data, clearly demonstrate the utility of the proposed method in real-time. Additionally, a comparative study with a direct learning network, that lacks forward model information, shows that the proposed method is more robust to DFOV variations. △ Less

Submitted 19 February, 2025; originally announced February 2025.

Comments: Accepted at IEEE ISBI 2025

Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning

Authors: Seohyun Lee, Wenzhi Fang, Anindya Bijoy Das, Seyyedali Hosseinalipour, David J. Love, Christopher G. Brinton

Abstract: Federated learning (FL) is vulnerable to backdoor attacks, where adversaries alter model behavior on target classification labels by embedding triggers into data samples. While these attacks have received considerable attention in horizontal FL, they are less understood for vertical FL (VFL), where devices hold different features of the samples, and only the server holds the labels. In this work,… ▽ More Federated learning (FL) is vulnerable to backdoor attacks, where adversaries alter model behavior on target classification labels by embedding triggers into data samples. While these attacks have received considerable attention in horizontal FL, they are less understood for vertical FL (VFL), where devices hold different features of the samples, and only the server holds the labels. In this work, we propose a novel backdoor attack on VFL which (i) does not rely on gradient information from the server and (ii) considers potential collusion among multiple adversaries for sample selection and trigger embedding. Our label inference model augments variational autoencoders with metric learning, which adversaries can train locally. A consensus process over the adversary graph topology determines which datapoints to poison. We further propose methods for trigger splitting across the adversaries, with an intensity-based implantation scheme skewing the server towards the trigger. Our convergence analysis reveals the impact of backdoor perturbations on VFL indicated by a stationarity gap for the trained model, which we verify empirically as well. We conduct experiments comparing our attack with recent backdoor VFL approaches, finding that ours obtains significantly higher success rates for the same main task performance despite not using server information. Additionally, our results verify the impact of collusion on attack performance. △ Less

Submitted 6 October, 2025; v1 submitted 16 January, 2025; originally announced January 2025.

Comments: This paper is currently under review in the IEEE/ACM Transactions on Networking Special Issue on AI and Networking

Self Pre-training with Adaptive Mask Autoencoders for Variable-Contrast 3D Medical Imaging

Authors: Badhan Kumar Das, Gengyan Zhao, Han Liu, Thomas J. Re, Dorin Comaniciu, Eli Gibson, Andreas Maier

Abstract: The Masked Autoencoder (MAE) has recently demonstrated effectiveness in pre-training Vision Transformers (ViT) for analyzing natural images. By reconstructing complete images from partially masked inputs, the ViT encoder gathers contextual information to predict the missing regions. This capability to aggregate context is especially important in medical imaging, where anatomical structures are fun… ▽ More The Masked Autoencoder (MAE) has recently demonstrated effectiveness in pre-training Vision Transformers (ViT) for analyzing natural images. By reconstructing complete images from partially masked inputs, the ViT encoder gathers contextual information to predict the missing regions. This capability to aggregate context is especially important in medical imaging, where anatomical structures are functionally and mechanically linked to surrounding regions. However, current methods do not consider variations in the number of input images, which is typically the case in real-world Magnetic Resonance (MR) studies. To address this limitation, we propose a 3D Adaptive Masked Autoencoders (AMAE) architecture that accommodates a variable number of 3D input contrasts per subject. A magnetic resonance imaging (MRI) dataset of 45,364 subjects was used for pretraining and a subset of 1648 training, 193 validation and 215 test subjects were used for finetuning. The performance demonstrates that self pre-training of this adaptive masked autoencoders can enhance the infarct segmentation performance by 2.8%-3.7% for ViT-based segmentation models. △ Less

Submitted 10 March, 2025; v1 submitted 15 January, 2025; originally announced January 2025.

Comments: 5 pages, ISBI 2025 accepted

Label Sharing Incremental Learning Framework for Independent Multi-Label Segmentation Tasks

Authors: Deepa Anand, Bipul Das, Vyshnav Dangeti, Antony Jerald, Rakesh Mullick, Uday Patil, Pakhi Sharma, Prasad Sudhakar

Abstract: In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures with shared encoders and multiple segmentation heads or shared weights with compound labels can also be made use of. This work proposes a novel label sharing fr… ▽ More In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures with shared encoders and multiple segmentation heads or shared weights with compound labels can also be made use of. This work proposes a novel label sharing framework where a shared common label space is constructed and each of the individual label sets are systematically mapped to the common labels. This transforms multiple datasets with disparate label sets into a single large dataset with shared labels, and therefore all the segmentation tasks can be addressed by learning a single model. This eliminates the need for task specific adaptations in network architectures and also results in parameter and data efficient models. Furthermore, label sharing framework is naturally amenable for incremental learning where segmentations for new datasets can be easily learnt. We experimentally validate our method on various medical image segmentation datasets, each involving multi-label segmentation. Furthermore, we demonstrate the efficacy of the proposed method in terms of performance and incremental learning ability vis-a-vis alternative methods. △ Less

Submitted 17 November, 2024; originally announced November 2024.