2 papers
cs.CR2024
Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
Depeng Chen, Hao Chen, Hulin Jin +2
Membership inference attacks (MIAs) are critical tools for assessing privacy risks and ensuring compliance with regulations like the General Data Protection Regulation (GDPR). Howe…
cs.LG2024
CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning
Depeng Chen, Xiao Liu, Jie Cui +1
Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the tra…