Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing

arXiv:2604.24162v1 Announce Type: cross Abstract: Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but typically incur high preparation costs and degrade utility via offline purification, or introduce severe...