ARTICLE Krivokuca_arxiv_PolyProtect_v3/IDIAP Towards Protecting Face Embeddings in Mobile Face Verification Scenarios Krivokuca, Vedrana Marcel, Sébastien EXTERNAL https://publications.idiap.ch/attachments/papers/2022/Krivokuca_arxiv_PolyProtect_v3.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Krivokuca_IEEET-BIOM_2022 Related documents arXiv 2022 Version 3 -- Accepted for publication in IEEE T-BIOM https://arxiv.org/abs/2110.00434v3 URL ARTICLE Krivokuca_IEEET-BIOM_2022/IDIAP Towards Protecting Face Embeddings in Mobile Face Verification Scenarios Krivokuca, Vedrana Marcel, Sébastien EXTERNAL https://publications.idiap.ch/attachments/papers/2022/Krivokuca_IEEET-BIOM_2022.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Krivokuca_arxiv_PolyProtect_v3 Related documents IEEE Transactions on Biometrics, Behavior, and Identity Science 4 1 117-134 2637-6407 2022 10.1109/TBIOM.2022.3140472 doi 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.