GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs

by   Dingfan Chen, et al.

In recent years, the success of deep learning has carried over from discriminative models to generative models. In particular, generative adversarial networks (GANs) have facilitated a new level of performance ranging from media manipulation to dataset re-generation. Despite the success, the potential risks of privacy breach stemming from GANs are less well explored. In this paper, we focus on membership inference attack against GANs that has the potential to reveal information about victim models' training data. Specifically, we present the first taxonomy of membership inference attacks, which encompasses not only existing attacks but also our novel ones. We also propose the first generic attack model that can be instantiated in various settings according to adversary's knowledge about the victim model. We complement our systematic analysis of attack vectors with a comprehensive experimental study, that investigates the effectiveness of these attacks w.r.t. model type, training configurations, and attack type across three diverse application scenarios ranging from images, over medical data to location data. We show consistent effectiveness in all the setups, which bridges the assumption gap and performance gap in previous study with a complete spectrum of performance across settings. We conclusively remind users to think over before publicizing any part of their models.


page 7

page 8

page 11

page 12

page 21

page 22


Reconstruction and Membership Inference Attacks against Generative Models

We present two information leakage attacks that outperform previous work...

BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models

The tremendous progress of autoencoders and generative adversarial netwo...

Generative Model: Membership Attack,Generalization and Diversity

This paper considers membership attacks to deep generative models, which...

TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing

Generative Adversarial Networks (GAN)-synthesized table publishing lets ...

This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces

Recently, generative adversarial networks (GANs) have achieved stunning ...

Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy

In recent years, diffusion models have achieved tremendous success in th...

Generative Models for Simulating Mobility Trajectories

Mobility datasets are fundamental for evaluating algorithms pertaining t...

Please sign up or login with your details

Forgot password? Click here to reset