CISPA
Browse
- No file added yet -

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

Download (7.09 MB)
conference contribution
posted on 2023-11-29, 18:12 authored by Dingfan Chen, Ning Yu, Yang ZhangYang Zhang, Mario FritzMario Fritz
Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of performance in a myriad of areas, ranging from media manipulation to sanitized dataset generation. Despite the great success, the potential risks of privacy breach caused by generative models have not been analyzed systematically. In this paper, we focus on membership inference attack against deep generative models that reveals information about the training data used for victim models. Specifically, we present the first taxonomy of membership inference attacks, encompassing not only existing attacks but also our novel ones. In addition, we propose the first generic attack model that can be instantiated in a large range of settings and is applicable to various kinds of deep generative models. Moreover, we provide a theoretically grounded attack calibration technique, which consistently boosts the attack performance in all cases, across different attack settings, data modalities, and training configurations. We complement the systematic analysis of attack performance by a comprehensive experimental study, that investigates the effectiveness of various attacks w.r.t. model type and training configurations, over three diverse application scenarios (i.e., images, medical data, and location data).

History

Preferred Citation

Dingfan Chen, Ning Yu, Yang Zhang and Mario Fritz. GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models. In: ACM Conference on Computer and Communications Security (CCS). 2020.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

ACM Conference on Computer and Communications Security (CCS)

Legacy Posted Date

2020-05-25

Open Access Type

  • Green

BibTeX

@inproceedings{cispa_all_3089, title = "GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models", author = "Chen, Dingfan and Yu, Ning and Zhang, Yang and Fritz, Mario", booktitle="{ACM Conference on Computer and Communications Security (CCS)}", year="2020", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC