ERASURE: Redefining Privacy Through Selective Machine Unlearning
Overview
ERASURE offers fully extensible built-in components, allowing users to define custom unlearning techniques, integrate custom and synthetic datasets, implement tailored evaluation metrics, and seamlessly work with state-of-the-art machine learning models.
Machine Unlearning (MU) enables selective removal of learned information from AI models without full retraining, addressing critical needs in:
- Data Privacy (GDPR Right to be Forgotten)
- Bias Mitigation
- Regulatory Compliance (AI Act, CCPA)
Resources
Related Work
- The Forget-Set Identification Problem – Machine Learning (Springer), 2025
- WIPE-OUT Workshop – ECML-PKDD 2025 & 2026