CISPA
Browse
cispa_all_3636.pdf (1.04 MB)

Property Inference Attacks Against GANs

Download (1.04 MB)
conference contribution
posted on 2023-11-29, 18:20 authored by Junhao Zhou, Yufei Chen, Chao Shen, Yang ZhangYang Zhang
While machine learning (ML) has made tremendous progress during the past decade, recent research has shown that ML models are vulnerable to various security and privacy attacks. So far, most of the attacks in this field focus on discriminative models, represented by classifiers. Meanwhile, little attention has been paid to the security and privacy risks of generative models, such as generative adversarial networks (GANs). In this paper, we propose the first set of training dataset property inference attacks against GANs. Concretely, the adversary aims to infer the macro-level training dataset property, i.e., the proportion of samples used to train a target GAN with respect to a certain attribute. A successful property inference attack can allow the adversary to gain extra knowledge of the target GAN’s training dataset, thereby directly violating the intellectual property of the target model owner. Also, it can be used as a fairness auditor to check whether the target GAN is trained with a biased dataset. Besides, property inference can serve as a building block for other advanced attacks, such as membership inference. We propose a general attack pipeline that can be tailored to two attack scenarios, including the full black-box setting and partial black-box setting. For the latter, we introduce a novel optimization framework to increase the attack efficacy. Extensive experiments over four representative GAN models on five property inference tasks show that our attacks achieve strong performance. In addition, we show that our attacks can be used to enhance the performance of membership inference against GANs.

History

Preferred Citation

Junhao Zhou, Yufei Chen, Chao Shen and Yang Zhang. Property Inference Attacks Against GANs. In: Network and Distributed System Security Symposium (NDSS). 2022.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

Network and Distributed System Security Symposium (NDSS)

Legacy Posted Date

2022-05-02

Open Access Type

  • Unknown

BibTeX

@inproceedings{cispa_all_3636, title = "Property Inference Attacks Against GANs", author = "Zhou, Junhao and Chen, Yufei and Shen, Chao and Zhang, Yang", booktitle="{Network and Distributed System Security Symposium (NDSS)}", year="2022", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC