Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks

arXiv:2403.02116v1 Announce Type: cross
Abstract: Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed for one specific type of attack and sacrifice significant utility or are soon broken by adaptive attacks. We address these limitations by proposing an information-theoretic defense framework, called Inf2Guard, against the three major types of inference attacks. Our framework, inspired by the …

aim arxiv attack attacks cs.cr cs.lg data dataset defenses framework information machine machine learning privacy private property sacrifice training training data utility vulnerable