conftrace_

safety region

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) safety guidance trigger (1) parameter granularity (1) safety identification dataset (1) utility dataset (1) malicious fine-tuning (1) model alignment (1)

Papers

Can LLM Safety Be Ensured by Constraining Parameter Regions? ACL 2026 SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger ACL 2026