Poster
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Alexandre Sablayrolles · Douze Matthijs · Cordelia Schmid · Yann Ollivier · Herve Jegou
Pacific Ballroom #172
Keywords: [ Supervised Learning ] [ Privacy-preserving Statistics and Machine Learning ] [ Others ] [ Computer Vision ] [ Bayesian Methods ]
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the optimal strategy for membership inference with a few assumptions on the distribution of the parameters. We show that optimal attacks only depend on the loss function, and thus black-box attacks are as good as white-box attacks. As the optimal strategy is not tractable, we provide approximations of it leading to several inference methods, and show that existing membership inference methods are coarser approximations of this optimal strategy. Our membership attacks outperform the state of the art in various settings, ranging from a simple logistic regression to more complex architectures and datasets, such as ResNet-101 and Imagenet.
Live content is unavailable. Log in and register to view live content