Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
Authors: Rongwu Xu, Xiaojian Li, Shuo Chen, Wei Xu | Published: 2025-02-17 | Updated: 2025-03-23
AIセキュリティポータルbot
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
Authors: Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang | Published: 2025-02-13 | Updated: 2025-05-26
A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack
Authors: Richard J. Preen, Jim Smith | Published: 2025-02-13 | Updated: 2025-06-12
RLSA-PFL: Robust Lightweight Secure Aggregation with Model Inconsistency Detection in Privacy-Preserving Federated Learning
Authors: Nazatul H. Sultan, Yan Bo, Yansong Gao, Seyit Camtepe, Arash Mahboubi, Hang Thanh Bui, Aufeef Chauhan, Hamed Aboutorab, Michael Bewong, Dineshkumar Singh, Praveen Gauravaram, Rafiqul Islam, Sharif Abuadbba | Published: 2025-02-13 | Updated: 2025-04-16
RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
Authors: Cheng Fang, Rishabh Dixit, Waheed U. Bajwa, Mert Gurbuzbalaban | Published: 2025-02-11
Trustworthy AI: Safety, Bias, and Privacy — A Survey
Authors: Xingli Fang, Jianwei Li, Varun Mulchandani, Jung-Eun Kim | Published: 2025-02-11 | Updated: 2025-06-11
Scalable and Ethical Insider Threat Detection through Data Synthesis and Analysis by LLMs
Authors: Haywood Gelman, John D. Hastings | Published: 2025-02-10 | Updated: 2025-04-07
Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study
Authors: Eric Aubinais, Philippe Formont, Pablo Piantanida, Elisabeth Gassiat | Published: 2025-02-10
Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs
Authors: Hiroki Watanabe, Motonobu Uchikoshi | Published: 2025-02-10 | Updated: 2025-04-24
From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
Authors: Awa Khouna, Julien Ferry, Thibaut Vidal | Published: 2025-02-07 | Updated: 2025-07-08