Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–6 of 6 results for author: Kasyap, H

Searching in archive cs. Search in all archives.
.
  1. arXiv:2608.00566  [pdf, ps, other

    cs.LG cs.AI

    Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors

    Authors: Niraj Kumar, Harsh Kasyap

    Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare. This ensures the model's transparency and acceptability. However, a few studies have examined potential attacks in the explainability pipeline. Adversaries can attempt to conceal algorithmic biases or backdoo… ▽ More

    Submitted 1 August, 2026; originally announced August 2026.

    Comments: 10 pages

  2. arXiv:2607.06612  [pdf, ps, other

    cs.CR cs.AI

    PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

    Authors: Harsh Kasyap, Anil Kumar Pradhan, Ugur Ilker Atmaca, Graham Cormode, Carsten Maple

    Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy. However, traditional FL frameworks rely on a centralized aggregation server and assume honest-but-curious clients, making them susceptible to both server-side inference and client-side poisoning attacks. Although recent work has explored s… ▽ More

    Submitted 7 July, 2026; originally announced July 2026.

    Comments: 18 pages

  3. arXiv:2602.22269  [pdf, ps, other

    cs.LG

    CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learning

    Authors: Arnab Nath, Harsh Kasyap

    Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data. However, shared local model updates remain vulnerable to inference and poisoning attacks. Secure aggregation schemes have been proposed to mitigate these attacks. In this work, we aim to understand how these techniques are implemented in quantum-assisted FL. Quantum Secure Aggregation (QSA) has been proposed, of… ▽ More

    Submitted 25 February, 2026; originally announced February 2026.

    Comments: 6 pages, 3 figures

  4. arXiv:2602.22242  [pdf, ps, other

    cs.CR cs.AI

    Analysis of LLMs Against Prompt Injection and Jailbreak Attacks

    Authors: Piyush Jaiswal, Aaditya Pratap, Shreyansh Saraswati, Harsh Kasyap, Somanath Tripathy

    Abstract: Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus, analyzing this risk has become a critical security requirement. This work evaluates prompt-injection and… ▽ More

    Submitted 24 February, 2026; originally announced February 2026.

    Comments: 12 pages, 5 figures, 6 tables

  5. arXiv:2510.12143  [pdf, ps, other

    cs.LG cs.CR

    Fairness-Constrained Optimization Attack in Federated Learning

    Authors: Harsh Kasyap, Minghong Fang, Zhuqing Liu, Carsten Maple, Somanath Tripathy

    Abstract: Federated learning (FL) is a privacy-preserving machine learning technique that facilitates collaboration among participants across demographics. FL enables model sharing, while restricting the movement of data. Since FL provides participants with independence over their training data, it becomes susceptible to poisoning attacks. Such collaboration also propagates bias among the participants, even… ▽ More

    Submitted 14 October, 2025; originally announced October 2025.

    Comments: To appear in IEEE TrustCom 2025

  6. arXiv:2407.19979  [pdf, other

    cs.CR

    Privacy-preserving Fuzzy Name Matching for Sharing Financial Intelligence

    Authors: Harsh Kasyap, Ugur Ilker Atmaca, Carsten Maple, Graham Cormode, Jiancong He

    Abstract: Financial institutions rely on data for many operations, including a need to drive efficiency, enhance services and prevent financial crime. Data sharing across an organisation or between institutions can facilitate rapid, evidence-based decision-making, including identifying money laundering and fraud. However, modern data privacy regulations impose restrictions on data sharing. For this reason,… ▽ More

    Submitted 8 November, 2024; v1 submitted 29 July, 2024; originally announced July 2024.

    Comments: 26 pages