1
Safety Targeted Embedding Exploit via Refinement
揭露低资源语言与混合代码切换可绕过LLM安全防护,揭示模型安全泛化的关键漏洞。
arXiv:2607.01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncert…