Aggregation and Embedding for Group Membership Verification

12/10/2018
by   Marzieh Gheisari, et al.
0

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 the error rates.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2020

Joint Learning of Assignment and Representation for Biometric Group Membership

This paper proposes a framework for group membership protocols preventin...
research
02/24/2020

Group Membership Verification with Privacy: Sparse or Dense?

Group membership verification checks if a biometric trait corresponds to...
research
04/23/2019

Privacy Preserving Group Membership Verification and Identification

When convoking privacy, group membership verification checks if a biomet...
research
06/17/2022

AggNet: Learning to Aggregate Faces for Group Membership Verification

In some face recognition applications, we are interested to verify wheth...
research
09/27/2021

FedIPR: Ownership Verification for Federated Deep Neural Network Models

Federated learning models must be protected against plagiarism since the...
research
04/18/2021

Federated Learning of User Verification Models Without Sharing Embeddings

We consider the problem of training User Verification (UV) models in fed...
research
04/16/2018

Community Member Retrieval on Social Media using Textual Information

This paper addresses the problem of community membership detection using...

Please sign up or login with your details

Forgot password? Click here to reset