Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Jailbreaks and attacks · Papers
Found 2 papers提出 ShallowJail，在推理时用转向向量改写隐藏状态实现越狱
- Published
- Evaluated models
- Qwen3-4B-Instruct-2507, Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
AttacksarXiv 2508.10029· 提出 Latent Fusion Jailbreak，插值有害与无害隐藏状态实施白盒越狱
- Published
- Evaluated models
- Vicuna-7B-v1.5, LLaMA-2-7B-Chat, Guanaco-7B and others5
You have reached the end