arXiv Open Access 2020

Against Membership Inference Attack: Pruning is All You Need

Yijue Wang Chenghong Wang Zigeng Wang Shanglin Zhou Hang Liu +3 lainnya

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.LG stat.ML

Penulis (8)

Yijue Wang

Chenghong Wang

Zigeng Wang

Shanglin Zhou

Hang Liu

Jinbo Bi

Caiwen Ding

Sanguthevar Rajasekaran

Format Sitasi

APA MLA BibTeX

Wang, Y., Wang, C., Wang, Z., Zhou, S., Liu, H., Bi, J. et al. (2020). Against Membership Inference Attack: Pruning is All You Need. https://arxiv.org/abs/2008.13578

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓