Membership Inference Attacks against Generative Models with Probabilistic Fluctuation

By Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang

Citations in the corpus

• Exploiting Unintended Feature Leakage in Collaborative Learning (2018, neutral): “Prior work described passive and active membership inference attacks against ML models [24, 53], but collaborative learning presents interesting new avenues for such inferences.”
• Dataset Inference: Ownership Resolution in Machine Learning (2021, unknown): “MI attacks are shown to work in white-(Leino & Fredrikson, 2020; Sablayrolles et al., 2019) as well as black-box scenarios against various target models including generative models (Hayes et al., 2019).”
• Differentially Private Data Generative Models (2018, unknown): “In addition, Hayes et al. [33] investigate the membership inference attack for generative models by using GANs [30] to detect overfitting and recognize training inputs.”
• Label-Only Membership Inference Attacks (2020, unknown): “Existing MI attacks exploit the higher confidence that models exhibit on their training data (Pyrgelis et al., 2017; Truex et al., 2018; Hayes et al., 2019; Salem et al., 2018).”