Boosting Model Inversion Attacks With Adversarial Examples
IEEE Transactions on Dependable and Secure Computing · 2024-05 · 21 (3) · 1451-1468
DOI: 10.1109/tdsc.2023.3285015 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, 2024-05. Verfasst von Shuai Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Australian Research Council Discovery.
Abstract (Originalsprache)
Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low attack accuracy, i.e., low classification accuracy of these reconstructed data by machine learning classifiers. Recent studies showed an alternative strategy of model inversion attacks, GAN-based optimization, can improve the attack accuracy effectively. However, these series of GAN-based attacks reconstruct only class-representative training data for a class, whereas learning-based attacks can reconstruct diverse data for different training data in each class. Hence, in this paper, we propose a new training paradigm for a learning-based model inversion attack that can achieve higher attack accuracy in a black-box setting. First, we regularize the training process of the attack model with an added semantic loss function and, second, we inject adversarial examples into the training data to increase the diversity of the class-related parts (i.e., he essential features for classification tasks) in training data. This scheme guides the attack model to pay more attention to the class-related parts of the original data during the data reconstruction process. The experimental results show that our method greatly boosts the performance of existing learning-based model inversion attacks. Even when no extra queries to the target model are allowed, the approach can still improve the attack accuracy of reconstructed data. This new attack shows that the severity of the threat from learning-based model inversion adversaries is underestimated and more robust defenses are required.
Förderung
- Australian Research Council Discovery
Zitieren
APA
Zhou, S., Zhu, T., Ye, D., Yu, X., & Zhou, W. (2024). Boosting Model Inversion Attacks With Adversarial Examples. IEEE Transactions on Dependable and Secure Computing, 21(3), 1451-1468. https://doi.org/10.1109/tdsc.2023.3285015
Vancouver
Zhou S, Zhu T, Ye D, Yu X, Zhou W. Boosting Model Inversion Attacks With Adversarial Examples. IEEE Transactions on Dependable and Secure Computing. 2024;21(3):1451-1468. doi:10.1109/tdsc.2023.3285015
BibTeX
@article{Zhou2024,
author = {Zhou, Shuai and Zhu, Tianqing and Ye, Dayong and Yu, Xin and Zhou, Wanlei},
title = {Boosting Model Inversion Attacks With Adversarial Examples},
journal = {IEEE Transactions on Dependable and Secure Computing},
year = {2024},
volume = {21},
number = {3},
pages = {1451--1468},
doi = {10.1109/tdsc.2023.3285015}
}
EUVIMED