5 papers
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…
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…
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…
Model Inversion Attack Against Deep Hashing
Dongdong Zhao, Qiben Xu, Ranxin Fang +1
Deep hashing improves retrieval efficiency through compact binary codes, yet it introduces severe and often overlooked privacy risks. The ability to reconstruct original training d…
Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition
Dongdong Zhao, Ranxin Fang, Changtian Song +2
Open Set Recognition (OSR) requires models not only to accurately classify known classes but also to effectively reject unknown samples. However, when unknown samples are semantica…