Membership Privacy Risks of Sharpness Aware Minimization
"成员推断攻击" 相关文章
MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
Win-k: Improved Membership Inference Attacks on Small Language Models
LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
Impact of Fine-Tuning Methods on Memorization in Large Language Models
