# dare
標記為「dare」的 4 篇文章
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
Model Merging & LoRA Composition Exploits
Exploiting model merging techniques (TIES, DARE, linear interpolation) and LoRA composition to introduce backdoors through individually benign model components.
model-mergingloratiesdaremergekitcompositionbackdoorsupply-chain
模型 Merging Risks
安全 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
模型合併與 LoRA 組合攻擊
利用模型合併技術（TIES、DARE、線性內插）與 LoRA 組合，透過個別無害的模型元件引入後門。
model-mergingloratiesdaremergekitcompositionbackdoorsupply-chain