Privacy Preserving Group Membership Verification and Identification

Abstract

When convoking privacy, group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member. Similarly, group membership identification states which group the individual belongs to, without knowing his/her identity. A recent contribution provides privacy and security for group membership protocols through the joint use of two mechanisms: quantizing biometric templates into discrete embeddings, and aggregating several templates into one group representation.This paper significantly improves that contribution because it jointly learns how to embed and aggregate instead of imposing fixed and hard coded rules. This is demonstrated by exposing the mathematical underpinnings of the learning stage before showing the improvements through an extensive series of experiments targeting face recognition.Overall, experiments show that learning yields an excellent trade-off between security / privacy and the verification / identification performances.

Joint Learning of Assignment and Representation for Biometric Group Membership

“…This is not the case in practice, so we give here an extra advantage to the curious server. Figure 4 compares security with AoE-ML [6] where the assignment was imposed randomly, i.e. not learned.…”

“…Security is preserved since nothing meaningful leaks from embedded data [8,9]. This paper revisits the core mechanism proposed by [6]. That work, however, is deterministic in the sense that it learns group representations based on predefined groups.…”

“…This adresses scenarios where the number of members is too big. Their signatures can not be packed into one unique group representation with a technique like [6]. Therefore, members are automatically assigned to different groups.…”

Group Membership Verification with Privacy: Sparse or Dense?

“…• EoA-SP and AoE-SP [1] (signal processing approach) • EoA-ML and AoE-ML [2] (machine learning approach) The drawback of these baselines is that the length m of the data structure is bounded. Here, it is set to maximum value, i.e.…”

“…[1] and [2], however face severe limitations. Basically, it seems impossible to create features representing groups having many members.…”