Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead
This addresses the need for trust in privacy-preserving machine learning for regulated domains like healthcare, but it is incremental as it builds on existing efforts.
The paper tackles the problem of verifying data removal in federated unlearning, proposing a framework called veriFUL to formalize verification entities, goals, and metrics, as current methods offer insufficient assurance for clients.
Federated unlearning (FUL) enables removing the data influence from the model trained across distributed clients, upholding the right to be forgotten as mandated by privacy regulations. FUL facilitates a value exchange where clients gain privacy-preserving control over their data contributions, while service providers leverage decentralized computing and data freshness. However, this entire proposition is undermined because clients have no reliable way to verify that their data influence has been provably removed, as current metrics and simple notifications offer insufficient assurance. We envision unlearning verification becoming a pivotal and trust-by-design part of the FUL life-cycle development, essential for highly regulated and data-sensitive services and applications like healthcare. This article introduces veriFUL, a reference framework for verifiable FUL that formalizes verification entities, goals, approaches, and metrics. Specifically, we consolidate existing efforts and contribute new insights, concepts, and metrics to this domain. Finally, we highlight research challenges and identify potential applications and developments for verifiable FUL and veriFUL.