Publication
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Lukas Struppek; Dominik Hintersdorf; Antonio De Almeida Correia; Antonia Adler; Kristian Kersting
In: Kamalika Chaudhuri; Stefanie Jegelka; Le Song; Csaba Szepesvári; Gang Niu; Sivan Sabato (Hrsg.). International Conference on Machine Learning. International Conference on Machine Learning (ICML-2022), July 17-23, Baltimore, Maryland, USA, Pages 20522-20545, Proceedings of Machine Learning Research, Vol. 162, PMLR, 2022.
Abstract
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research has developed generative MIAs that use generative adversarial networks (GANs) as image priors tailored to a specific target model. This makes the attacks time- and resource-consuming, inflexible, and susceptible to distributional shifts between datasets. To overcome these drawbacks, we present Plug & Play Attacks, which relax the dependency between the target model and image prior, and enable the use of a single GAN to attack a wide range of targets, requiring only minor adjustments to the attack. Moreover, we show that powerful MIAs are possible even with publicly available pre-trained GANs and under strong distributional shifts, for which previous approaches fail to produce meaningful results. Our extensive evaluation confirms the improved robustness and flexibility of Plug & Play Attacks and their ability to create high-quality images revealing sensitive class characteristics.