TY - GEN
T1 - Against Membership Inference Attack
T2 - 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
AU - Wang, Yijue
AU - Wang, Chenghong
AU - Wang, Zigeng
AU - Zhou, Shanglin
AU - Liu, Hang
AU - Bi, Jinbo
AU - Ding, Caiwen
AU - Rajasekaran, Sanguthevar
N1 - Publisher Copyright:
© 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85117367922&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117367922&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2021/432
DO - 10.24963/ijcai.2021/432
M3 - Conference contribution
AN - SCOPUS:85117367922
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3141
EP - 3147
BT - Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
A2 - Zhou, Zhi-Hua
PB - International Joint Conferences on Artificial Intelligence
Y2 - 19 August 2021 through 27 August 2021
ER -