PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeFace RecognitionSimilar Papers 제목 키워드 기반
NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers
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 ClassificationWhat's in a Name? Reducing Bias in Bios without Access to Protected Attributes
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 EmbeddingsMatched sample selection with GANs for mitigating attribute confounding
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+1Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
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…
FairnessFairMask: Better Fairness via Model-based Rebalancing of Protected Attributes
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