PrivEraserVerify: Efficient, Private, and Verifiable Federated Unlearning

2026-04-14

AI Summary

This work addresses the challenge that federated learning models tend to memorize users’ sensitive data, making it difficult to efficiently and verifiably fulfill the right to be forgotten. To this end, the paper proposes PrivEraserVerify, a unified framework that, for the first time, simultaneously achieves high efficiency, formal privacy guarantees, and decentralized verifiability in federated unlearning. By integrating an adaptive checkpointing mechanism, hierarchical differential privacy calibration, and non-intrusive fingerprint-based verification, the framework enables unlearning speeds 2–3 times faster than full retraining across multiple datasets, while significantly reducing accuracy degradation and supporting scalable privacy and verification assurances.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Privacy-enhancing technologies
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Federated learning (FL) enables collaborative model training without sharing raw data, offering a promising path toward privacy preserving artificial intelligence. However, FL models may still memorize sensitive information from participants, conflicting with the right to be forgotten (RTBF). To meet these requirements, federated unlearning has emerged as a mechanism to remove the contribution of departing clients. Existing solutions only partially address this challenge: FedEraser improves efficiency but lacks privacy protection, FedRecovery ensures differential privacy (DP) but degrades accuracy, and VeriFi enables verifiability but introduces overhead without efficiency or privacy guarantees. We present PrivEraserVerify (PEV), a unified framework that integrates efficiency, privacy, and verifiability into federated unlearning. PEV employs (i) adaptive checkpointing to retain critical historical updates for fast reconstruction, (ii) layer adaptive differentially private calibration to selectively remove client influence while minimizing accuracy loss, and (iii) fingerprint based verification, enabling participants to confirm unlearning in a decentralized and noninvasive manner. Experiments on image, handwritten character, and medical datasets show that PEV achieves up to 2 to 3 times faster unlearning than retraining, provides formal indistinguishability guarantees with reduced performance degradation, and supports scalable verification. To the best of our knowledge, PEV is the first framework to simultaneously deliver efficiency, privacy, and verifiability for federated unlearning, moving FL closer to practical and regulation compliant deployment.

Problem

• federated unlearning
• privacy
• verifiability
• right to be forgotten
• efficiency

Innovation

• federated unlearning
• differential privacy
• verifiability
• adaptive checkpointing
• privacy-preserving machine learning