Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

Autor:	Struppek, Lukas, Hintersdorf, Dominik, Correia, Antonio De Almeida, Adler, Antonia, Kersting, Kristian
Rok vydání:	2022
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by ICML 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2201.12179 Zobrazit plný text záznamu View this record from Arxiv