从期望危害到似然:LLM 智能体越狱的概率重构
提出 OPUR 攻击,用似然梯度优化对抗后缀越狱 LLM 智能体
- arXiv
- 2610.09973
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Attacker
- White-box
- Evaluated models
- Llama-3.1-8B-Instruct, Ministral-8B-Instruct-2410
- AttacksJailbreaks
- TechniqueGradient and representation optimization