#01
Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks
arXiv:2609.05794v1 Announce Type: cross Abstract: Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions and search for projection-matrix edits that suppress safety alignment while pres
推荐理由Bait-and-Recover: Poisoning Internal：arXiv:2609.05794v1 Announce Type: cross Abstract: Open-weight large language models。