Toward Verifiable Federated Unlearning
Framework, Challenges, and The Road Ahead
Thanh Linh Nguyen (Trinity College Dublin)
Marcela Tuler de Oliveira (TU Delft - Information and Communication Technology)
An Braeken (Vrije Universiteit Brussel)
Aaron Yi Ding (TU Delft - Information and Communication Technology)
Quoc Viet Pham (Trinity College Dublin)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Federated unlearning (FUL) enables removal of the data influence from a 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 FUL lifecycle development, essential for highly regulated and data-sensitive services and applications like health care. 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.
help_outline