Joint Learning of Assignment and Representation for Biometric Group Membership
This addresses privacy concerns in biometric systems for users and organizations, but appears incremental as it builds on existing group membership protocols.
The paper tackles the problem of protecting biometric data from reconstruction and identity inference by a curious server, proposing a framework that jointly learns embedding parameters, group representations, and assignments, with experiments showing a trade-off between security/privacy and verification/identification performance.
This paper proposes a framework for group membership protocols preventing the curious but honest server from reconstructing the enrolled biometric signatures and inferring the identity of querying clients. This framework learns the embedding parameters, group representations and assignments simultaneously. Experiments show the trade-off between security/privacy and verification/identification performances.