Center-Based Relaxed Learning Against Membership Inference Attacks

arXiv:2404.17674v1 Announce Type: new
Abstract: Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches and ideal models in performance and deployment costs. In particular, we observed that the privacy vulnerability of the model is closely correlated with the gap between the model's data-memorizing ability and generalization ability. To address this, we propose a new architecture-agnostic …

abstract arxiv attacks center costs cs.ai cs.cr cs.lg defense deployment gap however inference performance privacy strategies type