1
Jailbreak Attack Initializations as Extractors of Compliance Directions
揭秘越狱攻击初始化如何提取大模型内部安全方向，为理解AI对齐漏洞提供新视角。
arXiv:2502.09755v4 Announce Type: replace-cross Abstract: Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding…