1
Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs
LLM安全新突破：共享潜在结构实现后门统一检测与缓解，为模型防御提供通用方案。
arXiv:2606.07963v1 Announce Type: cross Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response fail…