AAAI 2026technical0 citations

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack

Jing Xue, Zhishen Sun, Haishan Ye, Luo Luo, Xiangyu Chang, Guang Dai

Abstract

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. This attack aims to determine whether a specific sample is part of the model

BibTeX
@inproceedings{aaai2026_privacyleaksbyad,
  title = {Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack},
  author = {Jing Xue and Zhishen Sun and Haishan Ye and Luo Luo and Xiangyu Chang and Guang Dai},
  booktitle = {AAAI 2026},
  year = {2026}
}
Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack · AAAI 2026