# PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

arXiv: https://arxiv.org/abs/2108.03764 · HTML: https://mlsanity.com/paper/2108.03764/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 9 Aug 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Demographic Bias in Biometrics: A Survey on an Emerging Challenge](https://mlsanity.com/paper/2003.02488/) (2020)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Live Face De-Identification in Video](https://mlsanity.com/paper/1911.08348/) (2019)
- [Analysis of Gender Inequality In Face Recognition Accuracy](https://mlsanity.com/paper/2002.00065/) (2020)
- [An All-In-One Convolutional Neural Network for Face Analysis](https://mlsanity.com/paper/1611.00851/) (2016)
- [UMDFaces: An Annotated Face Dataset for Training Deep Networks](https://mlsanity.com/paper/1611.01484/) (2016)
- [How Does Gender Balance In Training Data Affect Face Recognition Accuracy?](https://mlsanity.com/paper/2002.02934/) (2020)
- [Fairness GAN](https://mlsanity.com/paper/1805.09910/) (2018)
- [An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification](https://mlsanity.com/paper/1808.05508/) (2018)
- [Is Face Recognition Sexist? No, Gendered Hairstyles and Biology Are](https://mlsanity.com/paper/2008.06989/) (2020)
- [Beyond Identity: What Information Is Stored in Biometric Face Templates?](https://mlsanity.com/paper/2009.09918/) (2020)
- [Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealed](https://mlsanity.com/paper/1812.10902/) (2018)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [The Do's and Don'ts for CNN-based Face Verification](https://mlsanity.com/paper/1705.07426/) (2017)
- [How are attributes expressed in face DCNNs?](https://mlsanity.com/paper/1910.05657/) (2019)
- [Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers](https://mlsanity.com/paper/1807.11936/) (2018)
- [A Fast and Accurate System for Face Detection, Identification, and Verification](https://mlsanity.com/paper/1809.07586/) (2018)
- [On measuring the iconicity of a face](https://mlsanity.com/paper/1903.01581/) (2019)

## Built on by (most cited first, 30 of 38)

- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [Analyzing Bias in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2305.06402/) (2023)
- [FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification](https://mlsanity.com/paper/2303.08325/) (2023)
- [Towards Fair Face Verification: An In-depth Analysis of Demographic Biases](https://mlsanity.com/paper/2307.10011/) (2023)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition](https://mlsanity.com/paper/2211.15181/) (2022)
- [Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention](https://mlsanity.com/paper/2304.02284/) (2023)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation](https://mlsanity.com/paper/2112.09786/) (2021)
- [Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization](https://mlsanity.com/paper/2409.03303/) (2024)
- [Zero-shot racially balanced dataset generation using an existing biased StyleGAN2](https://mlsanity.com/paper/2305.07710/) (2023)
- [Gaussian Harmony: Attaining Fairness in Diffusion-based Face Generation Models](https://mlsanity.com/paper/2312.14976/) (2023)
- [Enhancing Fairness of Visual Attribute Predictors](https://mlsanity.com/paper/2207.05727/) (2022)
- [Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition](https://mlsanity.com/paper/2211.07245/) (2022)
- [CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems](https://mlsanity.com/paper/2407.13922/) (2024)
- [On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes](https://mlsanity.com/paper/2501.12020/) (2025)
- [A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2503.06451/) (2025)
- [A Differentiable Distance Approximation for Fairer Image Classification](https://mlsanity.com/paper/2210.04369/) (2022)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility](https://mlsanity.com/paper/2302.07917/) (2023)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable](https://mlsanity.com/paper/2605.10404/) (2026)
- [Fairly Private: Investigating The Fairness of Visual Privacy Preservation Algorithms](https://mlsanity.com/paper/2301.05012/) (2023)
- [Delving into Identify-Emphasize Paradigm for Combating Unknown Bias](https://mlsanity.com/paper/2302.11414/) (2023)
- [Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics](https://mlsanity.com/paper/2303.14411/) (2023)
- [Towards Fair and Robust Face Parsing for Generative AI: A Multi-Objective Approach](https://mlsanity.com/paper/2502.04391/) (2025)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)

## Abstract (arXiv)

Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained from any previously trained high-performing network to classify identities and simultaneously reduce encoding of sensitive attributes. This eliminates the need for end-to-end training. As a component of PASS, we present a novel discriminator training strategy that discourages a network from encoding protected attribute information. We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface. As a result, PASS descriptors outperform existing baselines in reducing gender and skintone bias on the IJB-C dataset, while maintaining a high verification accuracy.