Membership Feature Disentanglement Network

Heonseok Ha, Jaehee Jang, Yonghyun Jeong, Sungroh Yoon

Abstract: Membership inference (MI) determines whether a given data point is involved in the training of target machine learning model. Thus, the notion of MI relies on both the data feature and the model. The existing MI methods focus on the model only. We introduce a membership feature disentanglement network (MFDN) to approach MI from the perspective of data features. We assume that the data features can be disentangled into the membership features and class features. The membership features are those that enable MI, and class features refer to those that the network is trying to learn. MFDN disentangles these features by adversarial games between the encoders and auxiliary critic networks. It also visualizes the membership features using an inductive bias from the perspective of MI. We perform empirical evaluations to demonstrate that MFDN can disentangle membership features and class features.