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
Abstract
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.
BibTeX
@inproceedings{ijcai2021p432,
title = {Against Membership Inference Attack: Pruning is All You Need},
author = {Wang, Yijue and Wang, Chenghong and Wang, Zigeng and Zhou, Shanglin and Liu, Hang and Bi, Jinbo and Ding, Caiwen and Rajasekaran, Sanguthevar},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Zhi-Hua Zhou},
pages = {3141--3147},
year = {2021},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2021/432},
url = {https://doi.org/10.24963/ijcai.2021/432},
}