Aggregation and embedding for group membership verification

Marzieh Gheisari (1) , Teddy Furon (1) , Laurent Amsaleg (1) , Behrooz Razeghi (2) , Slava Voloshynovskiy (2)

1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
2 CVML - Computer Vision and Multimedia Laboratory [Geneve]

This paper proposes a group membership verification protocol preventing the curious but honest server from reconstructing the enrolled signatures and inferring the identity of querying clients. The protocol quantizes the signatures into discrete embeddings, making reconstruction difficult. It also aggregates multiple embeddings into representative values, impeding identification. Theoretical and experimental results show the trade-off between the security and error rates.

Mots clés: Index Terms-group representation; Group representation; data privacy; verification; aggregation; discrete embed- ding; Discrete embeddings

Domaines: Traitement du signal et de l'image [eess.SP]; Cryptographie et sécurité [cs.CR]

Marzieh Gheisari, Teddy Furon, Laurent Amsaleg, Behrooz Razeghi, Slava Voloshynovskiy. Aggregation and embedding for group membership verification. ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. pp.2592-2596, ⟨10.1109/ICASSP.2019.8682422⟩. ⟨hal-02091036v3⟩