Showing 1–8 of 8 results for author: Abed, J

LAAF: Logic-layer Automated Attack Framework A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems

Authors: Hammad Atta, Ken Huang, Kyriakos Rock Lambros, Yasir Mehmood, Zeeshan Baig, Mohamed Abdur Rahman, Manish Bhatt, M. Aziz Ul Haq, Muhammad Aatif, Nadeem Shahzad, Kamal Noor, Vineeth Sai Narajala, Hazem Ali, Jamel Abed

Abstract: Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which no automated red-teaming instrument existed. We present LAAF (Logic-layer Automated Attack Framework), the first automated red-teaming framework to combine an LPCI-specific technique taxonomy with stage-sequential seed es… ▽ More Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which no automated red-teaming instrument existed. We present LAAF (Logic-layer Automated Attack Framework), the first automated red-teaming framework to combine an LPCI-specific technique taxonomy with stage-sequential seed escalation - two capabilities absent from existing tools: Garak lacks memory-persistence and cross-session triggering; PyRIT supports multi-turn testing but treats turns independently, without seeding each stage from the prior breakthrough. LAAF provides: (i) a 49-technique taxonomy spanning six attack categories (Encoding~11, Structural~8, Semantic~8, Layered~5, Trigger~12, Exfiltration~5; see Table 1), combinable across 5 variants per technique and 6 lifecycle stages, yielding a theoretical maximum of 2,822,400 unique payloads ($49 \times 5 \times 1{,}920 \times 6$; SHA-256 deduplicated at generation time); and (ii) a Persistent Stage Breaker (PSB) that drives payload mutation stage-by-stage: on each breakthrough, the PSB seeds the next stage with a mutated form of the winning payload, mirroring real adversarial escalation. Evaluation on five production LLM platforms across three independent runs demonstrates that LAAF achieves higher stage-breakthrough efficiency than single-technique random testing, with a mean aggregate breakthrough rate of 84\% (range 83--86\%) and platform-level rates stable within 17 percentage points across runs. Layered combinations and semantic reframing are the highest-effectiveness technique categories, with layered payloads outperforming encoding on well-defended platforms. △ Less

Submitted 17 March, 2026; originally announced March 2026.

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.

Optimizing Solar Energy Production in the USA: Time-Series Analysis Using AI for Smart Energy Management

Authors: Istiaq Ahmed, Md Asif Ul Hoq Khan, MD Zahedul Islam, Md Sakibul Hasan, Tanaya Jakir, Arat Hossain, Joynal Abed, Muhammad Hasanuzzaman, Sadia Sharmeen Shatyi, Kazi Nehal Hasnain

Abstract: As the US rapidly moves towards cleaner energy sources, solar energy is fast becoming the pillar of its renewable energy mix. Even while solar energy is increasingly being used, its variability is a key hindrance to grid stability, storage efficiency, and system stability overall. Solar energy has emerged as one of the fastest-growing renewable energy sources in the United States, adding noticeabl… ▽ More As the US rapidly moves towards cleaner energy sources, solar energy is fast becoming the pillar of its renewable energy mix. Even while solar energy is increasingly being used, its variability is a key hindrance to grid stability, storage efficiency, and system stability overall. Solar energy has emerged as one of the fastest-growing renewable energy sources in the United States, adding noticeably to the country's energy mix. Retrospectively, the necessity of inserting the sun's energy into the grid without disrupting reliability and cost efficiencies highlights the necessity of good forecasting software and smart control systems. The dataset utilized for this research project comprised both hourly and daily solar energy production records collected from multiple utility-scale solar farms across diverse U.S. regions, including California, Texas, and Arizona. Training and evaluation of all models were performed with a time-based cross-validation scheme, namely, sliding window validation. Both the Random Forest and the XG-Boost models demonstrated noticeably greater and the same performance across each of the measures considered, with relatively high accuracy. The almost perfect and equal performance by the Random Forest and XG-Boost models also shows both models to have learned the patterns in the data very comprehensively, with high reliability in their predictions. By incorporating AI-powered time-series models like XG-Boost in grid management software, utility companies can dynamically modify storage cycles in real-time as well as dispatch and peak load planning, based on their predictions. AI-powered solar forecasting also has profound implications for renewable energy policy and planning, particularly as U.S. federal and state governments accelerate toward ambitious decarbonization goals. △ Less

Submitted 29 June, 2025; originally announced June 2025.

Open Catalyst Experiments 2024 (OCx24): Bridging Experiments and Computational Models

Authors: Jehad Abed, Jiheon Kim, Muhammed Shuaibi, Brook Wander, Boris Duijf, Suhas Mahesh, Hyeonseok Lee, Vahe Gharakhanyan, Sjoerd Hoogland, Erdem Irtem, Janice Lan, Niels Schouten, Anagha Usha Vijayakumar, Jason Hattrick-Simpers, John R. Kitchin, Zachary W. Ulissi, Aaike van Vugt, Edward H. Sargent, David Sinton, C. Lawrence Zitnick

Abstract: The search for low-cost, durable, and effective catalysts is essential for green hydrogen production and carbon dioxide upcycling to help in the mitigation of climate change. Discovery of new catalysts is currently limited by the gap between what AI-accelerated computational models predict and what experimental studies produce. To make progress, large and diverse experimental datasets are needed t… ▽ More The search for low-cost, durable, and effective catalysts is essential for green hydrogen production and carbon dioxide upcycling to help in the mitigation of climate change. Discovery of new catalysts is currently limited by the gap between what AI-accelerated computational models predict and what experimental studies produce. To make progress, large and diverse experimental datasets are needed that are reproducible and tested at industrially-relevant conditions. We address these needs by utilizing a comprehensive high-throughput characterization and experimental pipeline to create the Open Catalyst Experiments 2024 (OCX24) dataset. The dataset contains 572 samples synthesized using both wet and dry methods with X-ray fluorescence and X-ray diffraction characterization. We prepared 441 gas diffusion electrodes, including replicates, and evaluated them using zero-gap electrolysis for carbon dioxide reduction (CO$_2$RR) and hydrogen evolution reactions (HER) at current densities up to $300$ mA/cm$^2$. To find correlations with experimental outcomes and to perform computational screens, DFT-verified adsorption energies for six adsorbates were calculated on $\sim$20,000 inorganic materials requiring 685 million AI-accelerated relaxations. Remarkably from this large set of materials, a data driven Sabatier volcano independently identified Pt as being a top candidate for HER without having any experimental measurements on Pt or Pt-alloy samples. We anticipate the availability of experimental data generated specifically for AI training, such as OCX24, will significantly improve the utility of computational models in selecting materials for experimental screening. △ Less

Submitted 18 November, 2024; originally announced November 2024.

Comments: 38 pages, 22 figures

The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts

Authors: Richard Tran, Janice Lan, Muhammed Shuaibi, Brandon M. Wood, Siddharth Goyal, Abhishek Das, Javier Heras-Domingo, Adeesh Kolluru, Ammar Rizvi, Nima Shoghi, Anuroop Sriram, Felix Therrien, Jehad Abed, Oleksandr Voznyy, Edward H. Sargent, Zachary Ulissi, C. Lawrence Zitnick

Abstract: The development of machine learning models for electrocatalysts requires a broad set of training data to enable their use across a wide variety of materials. One class of materials that currently lacks sufficient training data is oxides, which are critical for the development of OER catalysts. To address this, we developed the OC22 dataset, consisting of 62,331 DFT relaxations (~9,854,504 single p… ▽ More The development of machine learning models for electrocatalysts requires a broad set of training data to enable their use across a wide variety of materials. One class of materials that currently lacks sufficient training data is oxides, which are critical for the development of OER catalysts. To address this, we developed the OC22 dataset, consisting of 62,331 DFT relaxations (~9,854,504 single point calculations) across a range of oxide materials, coverages, and adsorbates. We define generalized total energy tasks that enable property prediction beyond adsorption energies; we test baseline performance of several graph neural networks; and we provide pre-defined dataset splits to establish clear benchmarks for future efforts. In the most general task, GemNet-OC sees a ~36% improvement in energy predictions when combining the chemically dissimilar OC20 and OC22 datasets via fine-tuning. Similarly, we achieved a ~19% improvement in total energy predictions on OC20 and a ~9% improvement in force predictions in OC22 when using joint training. We demonstrate the practical utility of a top performing model by capturing literature adsorption energies and important OER scaling relationships. We expect OC22 to provide an important benchmark for models seeking to incorporate intricate long-range electrostatic and magnetic interactions in oxide surfaces. Dataset and baseline models are open sourced, and a public leaderboard is available to encourage continued community developments on the total energy tasks and data. △ Less

Submitted 7 March, 2023; v1 submitted 17 June, 2022; originally announced June 2022.

Comments: 50 pages, 14 figures

Accelerated chemical space search using a quantum-inspired cluster expansion approach

Authors: Hitarth Choubisa, Jehad Abed, Douglas Mendoza, Zhenpeng Yao, Ziyun Wang, Brandon Sutherland, Alán Aspuru-Guzik, Edward H Sargent

Abstract: To enable the accelerated discovery of materials with desirable properties, it is critical to develop accurate and efficient search algorithms. Quantum annealers and similar quantum-inspired optimizers have the potential to provide accelerated computation for certain combinatorial optimization challenges. However, they have not been exploited for materials discovery due to absence of compatible op… ▽ More To enable the accelerated discovery of materials with desirable properties, it is critical to develop accurate and efficient search algorithms. Quantum annealers and similar quantum-inspired optimizers have the potential to provide accelerated computation for certain combinatorial optimization challenges. However, they have not been exploited for materials discovery due to absence of compatible optimization mapping methods. Here we show that by combining cluster expansion with a quantum-inspired superposition technique, we can lever quantum annealers in chemical space exploration for the first time. This approach enables us to accelerate the search of materials with desirable properties order 10-50 times faster than genetic algorithms and bayesian optimizations, with a significant improvement in ground state prediction accuracy. Levering this, we search chemical space for discovery of acidic oxygen evolution reaction (OER) catalysts and find a promising previously unexplored chemical family of Ru-Cr-Mn-Sb-O$_2$. The best catalyst in this chemical family show a mass activity 8 times higher than state-of-art RuO$_2$ and maintain performance for 180 hours while operating at 10mA/cm$^2$ in acidic 0.5 M $H_2SO_4$ electrolyte. △ Less

Submitted 13 December, 2022; v1 submitted 18 May, 2022; originally announced May 2022.

Edge-degenerate families of $Ψ$Do's on an infinite cylinder

Authors: Jamil Abed, Bert Wolfgang Schulze

Abstract: We establish a parameter-dependent pseudo-differential calculus on an infinite cylinder, regarded as a manifold with conical exits to infinity. The parameters are involved in edge-degenerate form, and we formulate the operators in terms of operator-valued amplitude functions. We establish a parameter-dependent pseudo-differential calculus on an infinite cylinder, regarded as a manifold with conical exits to infinity. The parameters are involved in edge-degenerate form, and we formulate the operators in terms of operator-valued amplitude functions. △ Less

Submitted 28 January, 2009; v1 submitted 14 January, 2009; originally announced January 2009.

Comments: Keywords. Edge-degenerate operators, parameter-dependent pseudo-differential operators, norm estimates with respect to a parameter

MSC Class: 35S35; 35J70

Operators with Corener-degenerate Symbols

Authors: Jamil Abed, Bert-Wolfgang Schulze

Abstract: We establish elements of a new approch to ellipticity and parametrices within operator algebras on a manifold with higher singularities, only based on some general axiomatic requirements on parameter-dependent operators in suitable scales of spaces. The idea is to model an iterative process with new generations of parameter-dependent operator theories, together with new scales of spaces that sat… ▽ More We establish elements of a new approch to ellipticity and parametrices within operator algebras on a manifold with higher singularities, only based on some general axiomatic requirements on parameter-dependent operators in suitable scales of spaces. The idea is to model an iterative process with new generations of parameter-dependent operator theories, together with new scales of spaces that satisfy analogous requirements as the original ones, now on a corresponding higher level. The "full" calculus is voluminous; so we content ourselves here with some typical aspects such as symbols in terms of order reducing families, classes of relevant examples, and operators near a corner point. △ Less

Submitted 9 February, 2008; v1 submitted 17 January, 2008; originally announced January 2008.

Comments: 40 pages

MSC Class: 35J70