The Role of Class Information in Model Inversion Attacks Against Image Deep Learning Classifiers

Model inversion attacks can reconstruct the training samples of victim deep learning models. The existing efforts heavily rely on auxiliary information of the target samples (prior target information) to achieve their adversarial goals. However, prior target information is hard to obtain in practice. In this article, we explore the effect of class information in model inversion attacks to reduce the reliance of prior target information. Our contributions on class information exploitation are two-fold. First, we propose a supervised inversion model, Supervised Model Inversion (SMI). The proposed inversion model learns pixel-level features and data-to-class features from the rounded-outputs of the victim model and labeled auxiliary dataset. Second, we leverage victim model's rounded-outputs to guide the optimization of reconstructing inversion samples after trained inversion model. Our experimental results show that inversion samples reconstructed by SMI are more visually plausible with more details, comparing to the three representative model inversion attacks. We further perform an extensive study on various auxiliary dataset settings. It is found that the class combination in the auxiliary dataset rather than the number of classes that determines the quality of inversion samples. The ground-truth labels can improve the qualities of inversion samples but not essential to inversion attacks.