# safety-loss
2 articlestagged with “safety-loss”
Model Merging Risks
Security risks in model and adapter merging workflows -- how merging adapters from untrusted sources can introduce vulnerabilities, exploit merge algorithm properties, and cause safety property loss through TIES, DARE, SLERP, and linear interpolation.
model-mergingtiesdareslerpadapter-mergesafety-lossfine-tuning-security
Safety Loss During Model Distillation
Research on how safety alignment degrades during knowledge distillation from larger to smaller models.
frontier-researchdistillationsafety-lossresearch