Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

LOGAN: Membership Inference Attacks Against Generative Models

LOGAN: Membership Inference Attacks Against Generative Models AbstractGenerative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator’s capacity to learn statistical differences in distributions. We present attacks based on both white-box and black-box access to the target model, against several state-of-the-art generative models, over datasets of complex representations of faces (LFW), objects (CIFAR-10), and medical images (Diabetic Retinopathy). We also discuss the sensitivity of the attacks to different training parameters, and their robustness against mitigation strategies, finding that defenses are either ineffective or lead to significantly worse performances of the generative models in terms of training stability and/or sample quality. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Proceedings on Privacy Enhancing Technologies de Gruyter

LOGAN: Membership Inference Attacks Against Generative Models

Download PDF
20 pages

Loading next page...
 
/lp/de-gruyter/logan-membership-inference-attacks-against-generative-models-td9EzWUIF7
Publisher
de Gruyter
Copyright
© 2019 Jamie Hayes et al., published by Sciendo
ISSN
2299-0984
eISSN
2299-0984
DOI
10.2478/popets-2019-0008
Publisher site
See Article on Publisher Site

Abstract

AbstractGenerative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator’s capacity to learn statistical differences in distributions. We present attacks based on both white-box and black-box access to the target model, against several state-of-the-art generative models, over datasets of complex representations of faces (LFW), objects (CIFAR-10), and medical images (Diabetic Retinopathy). We also discuss the sensitivity of the attacks to different training parameters, and their robustness against mitigation strategies, finding that defenses are either ineffective or lead to significantly worse performances of the generative models in terms of training stability and/or sample quality.

Journal

Proceedings on Privacy Enhancing Technologies – de Gruyter

Published: Jan 1, 2019

There are no references for this article.