Towards Protecting Face Embeddings in Mobile Face Verification Scenarios
Authors:
Preprint
Abstract
This paper proposes PolyProtect, a method for protecting the sensitive face embeddings that are used to represent people's faces in neural-network-based face verification systems. PolyProtect transforms a face embedding to a more secure template, using a mapping based on multivariate polynomials parameterised by user-specific coefficients and exponents. In this work, PolyProtect is evaluated on two open-source face recognition systems in a cooperative-user mobile face verification context, under the toughest threat model that assumes a fully-informed attacker with complete knowledge of the system and all its parameters. Results indicate that PolyProtect can be tuned to achieve a satisfactory trade-off between the recognition accuracy of the PolyProtected face verification system and the irreversibility of the PolyProtected templates. Furthermore, PolyProtected templates are shown to be effectively unlinkable, especially if the user-specific parameters employed in the PolyProtect mapping are selected in a non-naive manner. The evaluation is conducted using practical methodologies with tangible results, to present realistic insight into the method's robustness as a face embedding protection scheme in practice. This work is fully reproducible using the publicly available code at: https://gitlab.idiap.ch/bob/bob.paper.polyprotect_2021.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Deep face fuzzy vault: Implementation and performanceComputers & Security, 2022
- Secure Triplet Loss: Achieving Cancelability and Non-Linkability in End-to-End Deep BiometricsIEEE Transactions on Biometrics, Behavior, and Identity Science, 2020
- Beyond Identity: What Information Is Stored in Biometric Face Templates?2020
- SecureFace: Face Template ProtectionIEEE Transactions on Information Forensics and Security, 2020
- Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protection2019
- Face template protection using deep LDPC codes learningIET Biometrics, 2019
- The Unsolvability of the Quintic2018
- On the Reconstruction of Face Images from Deep Face TemplatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- General Framework to Evaluate Unlinkability in Biometric Template Protection SystemsIEEE Transactions on Information Forensics and Security, 2017
- A Fuzzy Vault SchemeDesigns, Codes and Cryptography, 2006