Against Membership Inference Attack: Pruning is All You Need

Wang, Yijue; Wang, Chenghong; Wang, Zigeng; Zhou, Shanglin; Liu, Hang; Bi, Jinbo; Ding, Caiwen; Rajasekaran, Sanguthevar

doi:10.24963/ijcai.2021/432

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

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3141-3147.

https://doi.org/10.24963/ijcai.2021/432

Keywords

Machine Learning: Deep Learning
Multidisciplinary Topics and Applications: Security and Privacy

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.

Yijue Wang, Chenghong Wang, Zigeng Wang, Shanglin Zhou, Hang Liu, Jinbo Bi, Caiwen Ding, and Sanguthevar Rajasekaran. 2021. Against Membership Inference Attack: Pruning is All You Need. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3141–3147. https://doi.org/10.24963/ijcai.2021/432

@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    = {Prof. 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},
}

TY  - CPAPER
TI  - Against Membership Inference Attack: Pruning is All You Need
AU  - Wang, Yijue
AU  - Wang, Chenghong
AU  - Wang, Zigeng
AU  - Zhou, Shanglin
AU  - Liu, Hang
AU  - Bi, Jinbo
AU  - Ding, Caiwen
AU  - Rajasekaran, Sanguthevar
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3141
EP  - 3147
DO  - 10.24963/ijcai.2021/432
UR  - https://doi.org/10.24963/ijcai.2021/432
ER  -