GuardrailAgent defends LLMs against adaptive jailbreak attacks
Multi-agent framework updates knowledge base from attack summaries to achieve 93.1% detection on over ten jailbreaks.
Stories per day · 30 days
1 RSS
3 stories, newest first · one card per story
Stories tagged #jailbreak-defense
ShallowDefend puts an explicit safety decision before multi-turn replies
Assess, Decide, Respond is trained with reinforcement learning and led multi-turn safety on 14 benchmarks across two model families.
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Researchers introduce Decoy Direction Optimization, a cheap weight-editing defense that blinds refusal-direction ablation attacks against open-weight LLM safety guardrails.