Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition

Face recognition embeddings encode identity, but they also encode other factors such as gender and ethnicity. Depending on how these factors are used by a downstream system, separating them from the information needed for verification is important for both privacy and fairness. We propose Variational Latent Entropy Estimation Disentanglement (VLEED), a post-hoc method that transforms pretrained embeddings with a variational autoencoder and encourages a distilled representation where the categorical variable of interest is separated from identity-relevant information. VLEED uses a mutual information-based objective realised through the estimation of the entropy of the categorical attribute in the latent space, and provides stable training with fine-grained control over information removal. We evaluate our method on IJB-C, RFW, and VGGFace2 for gender and ethnicity disentanglement, and compare it to various state-of-the-art methods. We report verification utility, predictability of the disentangled variable under linear and nonlinear classifiers, and group disparity metrics based on false match rates. Our results show that VLEED offers a wide range of privacy-utility tradeoffs over existing methods and can also reduce recognition bias across demographic groups.

MLP-Hash: Protecting Face Templates via Hashing of Randomized Multi-Layer Perceptron

Applications of face recognition systems for authentication purposes are growing rapidly. Although state-of-the-art (SOTA) face recognition systems have high recognition performance, the features which are extracted for each user and are stored in the system's database contain privacy-sensitive information. Accordingly, compromising this data would jeopardize users' privacy. In this paper, we propose a new cancelable template protection method, dubbed MLP-hash, which generates protected templates by passing the extracted features through a user-specific randomly-weighted multi-layer perceptron (MLP) and binarizing the MLP output. We evaluated the unlinkability, irreversibility, and recognition performance of our proposed biometric template protection method to fulfill the ISO/IEC 30136 standard requirements. Our experiments with SOTA face recognition systems on the MOBIO and LFW datasets show that our method has competitive performance with the BioHashing and IoM Hashing (IoM-GRP and IoM-URP) template protection algorithms. We provide an open-source implementation of all the experiments presented in this paper so that other researchers can verify our findings and build upon our work.

Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques

This paper presents a survey of biometric template protection (BTP) methods for securing face templates in neural-network-based face recognition systems. The BTP methods are categorised into two types: Non-NN and NN-learned. Non-NN methods use a neural network (NN) as a feature extractor, but the BTP part is based on a non-NN algorithm applied at image-level or feature-level. In contrast, NN-learned methods specifically employ a NN to learn a protected template from the unprotected face image/features. We present examples of Non-NN and NN-learned face BTP methods from the literature, along with a discussion of the two categories' comparative strengths and weaknesses. We also investigate the techniques used to evaluate these BTP methods, in terms of the three most common criteria: recognition accuracy, irreversibility, and renewability/unlinkability. As expected, the recognition accuracy of protected face recognition systems is generally evaluated using the same (empirical) techniques employed for evaluating standard (unprotected) biometric systems. On the contrary, most irreversibility and renewability/unlinkability evaluations are based on theoretical assumptions/estimates or verbal implications, with no empirical validation in a practical face recognition context. So, we recommend a greater focus on empirical evaluation strategies, to provide more concrete insights into the irreversibility and renewability/unlinkability of face BTP methods in practice. An exploration of the reproducibility of the studied BTP works, in terms of the public availability of their implementation code and evaluation datasets/procedures, suggests that it would currently be difficult for the BTP community to faithfully replicate (and thus validate) most of the reported findings. So, we advocate for a push towards reproducibility, in the hope of furthering our understanding of the face BTP research field.

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

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 verification systems in a mobile application 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. The code to fully reproduce this work is available at: https://gitlab.idiap.ch/bob/bob.paper.polyprotect_2021.