{"ID":2872909,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07456","arxiv_id":"2509.07456","title":"Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting","abstract":"Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires retraining from scratch or redesigning data pipelines, recent advances in machine unlearning provide a promising alternative for post-hoc model correction. In this work, we investigate \\textit{Bias-Aware Machine Unlearning}, a paradigm that selectively removes biased samples or feature representations to mitigate diverse forms of bias in vision models. Building on privacy-preserving unlearning techniques, we evaluate various strategies including Gradient Ascent, LoRA, and Teacher-Student distillation. Through empirical analysis on three benchmark datasets, CUB-200-2011 (pose bias), CIFAR-10 (synthetic patch bias), and CelebA (gender bias in smile detection), we demonstrate that post-hoc unlearning can substantially reduce subgroup disparities, with improvements in demographic parity of up to \\textbf{94.86\\%} on CUB-200, \\textbf{30.28\\%} on CIFAR-10, and \\textbf{97.37\\%} on CelebA. These gains are achieved with minimal accuracy loss and with methods scoring an average of 0.62 across the 3 settings on the joint evaluation of utility, fairness, quality, and privacy. Our findings establish machine unlearning as a practical framework for enhancing fairness in deployed vision systems without necessitating full retraining.","short_abstract":"Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires retraining from scratch or redesigning data pipelines, recent advances in machine u...","url_abs":"https://arxiv.org/abs/2509.07456","url_pdf":"https://arxiv.org/pdf/2509.07456v1","authors":"[\"Sai Siddhartha Chary Aylapuram\",\"Veeraraju Elluru\",\"Shivang Agarwal\"]","published":"2025-09-09T07:25:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"LoRA\"]","has_code":false}