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

Source: [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](<https://www.sota2.com/research/paper/68fa6a7a1e209131cea286ef>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:26:28.956Z

Authors: Prithviraj Dhar, Joshua Gleason, Aniket Roy, Carlos D. Castillo, Rama Chellappa

Published: 2021-08-09T00:39:22.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Face Recognition on LFW 1.0 (full set)](<https://www.sota2.com/research/sota/face-recognition-on-lfw-1-0-full-set.md>): Face Recognition; LFW 1.0 (full set); FRR @ FAR: 10.7.

- [Face Verification on IJB-C 1:1 protocol (test)](<https://www.sota2.com/research/sota/face-verification-on-ijb-c-1-1-protocol-test.md>): Face Verification; IJB-C 1:1 protocol (test); FRR @ FAR=1e-4 (%): 0.09.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.03764>)

[PDF](<https://arxiv.org/pdf/2108.03764.pdf>)