{"ID":2868326,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16525","arxiv_id":"2509.16525","title":"Causal Fuzzing for Verifying Machine Unlearning","abstract":"As machine learning models become increasingly embedded in decision-making systems, the ability to \"unlearn\" targeted data or features is crucial for enhancing model adaptability, fairness, and privacy in models which involves expensive training. To effectively guide machine unlearning, a thorough testing is essential. Existing methods for verification of machine unlearning provide limited insights, often failing in scenarios where the influence is indirect. In this work, we propose CAFÉ, a new causality based framework that unifies datapoint- and feature-level unlearning for verification of black-box ML models. CAFÉ evaluates both direct and indirect effects of unlearning targets through causal dependencies, providing actionable insights with fine-grained analysis. Our evaluation across five datasets and three model architectures demonstrates that CAFÉ successfully detects residual influence missed by baselines while maintaining computational efficiency.","short_abstract":"As machine learning models become increasingly embedded in decision-making systems, the ability to \"unlearn\" targeted data or features is crucial for enhancing model adaptability, fairness, and privacy in models which involves expensive training. To effectively guide machine unlearning, a thorough testing is essential....","url_abs":"https://arxiv.org/abs/2509.16525","url_pdf":"https://arxiv.org/pdf/2509.16525v1","authors":"[\"Anna Mazhar\",\"Sainyam Galhotra\"]","published":"2025-09-20T04:19:37Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}