Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
arXiv:2602.19396v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect …
Amirhossein Farzam, Majid Behabahani, Mani Malek, Yuriy Nevmyvaka, Guillermo Sapiro
조회수 50회