Publications
Detailed Information
Membership Feature Disentanglement Network
Cited 0 time in
Web of Science
Cited 2 time in Scopus
- Authors
- Issue Date
- 2022-05
- Publisher
- Association for Computing Machinery, Inc
- Citation
- ASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security, pp.364-376
- Abstract
- © 2022 ACM.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.
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.