Uncovering Gender Biases in Human-AI Platforms

Abstract

As part of my PhD studies, I am focusing on the broad problem of gender related biases in Human-AI systems, making a three-fold contribution to every part of the Responsible AI pipeline-- (i) Adversarial Audits in different human-AI platforms to identify biases against binary & non-binary gender groups, (ii) Novel gender-inclusive datasets and (iii) Low-resource bias mitigation algorithms. The Human-AI systems that I am studying as part of my PhD thesis are-- (a) Face Recognition Systems (FRSs), (b) e-commerce platforms, (c) text-based gender analyzers and (d) Vision Language Models (VLMs). My thesis is divided into three parts-- (i) Adversarial audit of FRSs for binary genders, (ii) Data-centric and model-centric bias mitigation in FRSs for binary genders, and (iii) Audit of non-binary gender bias in other Human-AI systems-- visual-search enabled e-commerce, text-based gender analyzers and VLMs.