2 papers
cs.AI2026
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
Jiacheng Liang, Yao Ma, Tharindu Kumarage +5
Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) ca…
cs.LG2026
Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa +8
Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical chall…