SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode refusal behavior while preserving task performance on legitimate inputs. We revisit recent layer-wise safety diagnostics and find that safety sensitivity is signed: scaling diff...
Hui Zhang, Ya-Chao Yuan, Jia-Yun Wang et al.
· 0 citations