Defending Against Membership Inference Attacks With High Utility by GAN
IEEE Transactions on Dependable and Secure Computing · 01.05.2023 · 20 (3) · 2144-2157
DOI: 10.1109/tdsc.2022.3174569 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, erschienen am 01.05.2023. Verfasst von Li Hu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The success of machine learning (ML) depends on the availability of large-scale datasets. However, recent studies have shown that models trained on such datasets are vulnerable to privacy attacks, among which membership inference attack (MIA) brings serious privacy risk. MIA allows an adversary to infer whether a sample belongs to the training dataset of the target model or not. Though a variety of defenses against MIA have been proposed such as differential privacy and adversarial regularization, they also result in lower model accuracy and thus make the models less unusable. In this article, aiming at maintaining the accuracy while protecting the privacy against MIA, we propose a new defense against membership inference attacks by generative adversarial network (GAN). Specifically, sensitive data is used to train a GAN, then the GAN generate the data for training the actual model. To ensure that the model trained with GAN on small datasets can has high utility, two different GAN structures with special training techniques are utilized to deal with the image data and table data, respectively. Experiment results show that the defense is more effective on different data sets against the existing attack schemes, and is more efficient compared with most advanced MIA defenses.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Hu, L., Li, J., Lin, G., Peng, S., Zhang, Z., Zhang, Y., & Dong, C. (2023). Defending Against Membership Inference Attacks With High Utility by GAN. IEEE Transactions on Dependable and Secure Computing, 20(3), 2144-2157. https://doi.org/10.1109/tdsc.2022.3174569
Vancouver
Hu L, Li J, Lin G, Peng S, Zhang Z, Zhang Y, et al. Defending Against Membership Inference Attacks With High Utility by GAN. IEEE Transactions on Dependable and Secure Computing. 2023;20(3):2144-2157. doi:10.1109/tdsc.2022.3174569
BibTeX
@article{Hu2023,
author = {Hu, Li and Li, Jin and Lin, Guanbiao and Peng, Shiyu and Zhang, Zhenxin and Zhang, Yingying and Dong, Changyu},
title = {Defending Against Membership Inference Attacks With High Utility by GAN},
journal = {IEEE Transactions on Dependable and Secure Computing},
year = {2023},
volume = {20},
number = {3},
pages = {2144--2157},
doi = {10.1109/tdsc.2022.3174569}
}
EUVIMED