Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Rethinking Backdoor Repair Evaluation: Distinguishing Aggregate Clean Utility from Benign Performance Preservation
Baogang Song, Changtian Song, Jian Chen +4
Backdoor repair aims to suppress malicious behavior in compromised models while preserving benign task performance. Existing studies typically evaluate these objectives using Attac…
cs.CR2026
Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage
Dongdong Zhao, Can Li, Xiang Yao +3
Existing backdoor attacks often become effective immediately after backdoor implantation and may therefore be exposed before exploitation. Machine unlearning activated dormant back…
cs.CR2026
Discard the Dross and Select the Essential: Pre-query Sample Selection for Black-box Membership Inference Attacks
Dongdong Zhao, Jinrong Hu, Changtian Song +3
Black-box membership inference attacks (MIAs) rely on target-model queries to infer whether candidate samples were used for training. However, membership signals are highly non-uni…