Against Membership Inference Attack: Pruning is All You Need
Against Membership Inference Attack: Pruning is All You Need
Yijue Wang, Chenghong Wang, Zigeng Wang, Shanglin Zhou, Hang Liu, Jinbo Bi, Caiwen Ding, Sanguthevar Rajasekaran
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 3141-3147.
https://doi.org/10.24963/ijcai.2021/432
The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge, we envision that the weight pruning technique will help DNNs against MIA while reducing model storage and computational operation. In this work, we propose a pruning algorithm, and we show that the proposed algorithm can find a subnetwork that can prevent privacy leakage from MIA and achieves competitive accuracy with the original DNNs. We also verify our theoretical insights with experiments. Our experimental results illustrate that the attack accuracy using model compression is up to 13.6% and 10% lower than that of the baseline and Min-Max game, accordingly.
Keywords:
Machine Learning: Deep Learning
Multidisciplinary Topics and Applications: Security and Privacy