paper-with-me

Papers

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

2021-08-09 · ICCV 2021 10 · Prithviraj Dhar, Joshua Gleason, Aniket Roy, Carlos D. Castillo, Rama Chellappa

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.

📄 PDF Abstract BibTeX arXiv:2108.03764

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeFace Recognition

Similar Papers 제목 키워드 기반

NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers

2024-07-01 · Salvatore Greco, Ke Zhou, Licia Capra, Tania Cerquitelli 외

AI regulations are expected to prohibit machine learning models from using sensitive attributes during training. However, the latest Natural Language Processing (NLP) classifiers, which rely on deep learning, operate as …

Occupation predictionSentiment AnalysisToxic Comment Classification

What's in a Name? Reducing Bias in Bios without Access to Protected Attributes

2019-04-10 · NAACL 2019 6 · Alexey Romanov, Maria De-Arteaga, Hanna Wallach, Jennifer Chayes 외

There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two…

Word Embeddings

Matched sample selection with GANs for mitigating attribute confounding

2021-03-24 · Chandan Singh, Guha Balakrishnan, Pietro Perona

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark d…

AttributeFace GenerationGender Bias DetectionGenerative Adversarial Network+1

Bias Mitigation Framework for Intersectional Subgroups in Neural Networks

2022-12-26 · Narine Kokhlikyan, Bilal Alsallakh, Fulton Wang, Vivek Miglani 외

We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating one kind of bias by incorporating comple…

Fairness

FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes

2021-10-03 · Kewen Peng, Joymallya Chakraborty, Tim Menzies

Context: Machine learning software can generate models that inappropriately discriminate against specific protected social groups (e.g., groups based on gender, ethnicity, etc). Motivated by those results, software engin…

Fairness