Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915738830241792 |
|---|---|
| author | Nguyen, Thanh Linh de Oliveira, Marcela Tuler Braeken, An Ding, Aaron Yi Pham, Quoc-Viet |
| author_facet | Nguyen, Thanh Linh de Oliveira, Marcela Tuler Braeken, An Ding, Aaron Yi Pham, Quoc-Viet |
| contents | 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. This article aims to provide a comprehensive resource for researchers and practitioners to navigate and advance the field of verifiable FUL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead Nguyen, Thanh Linh de Oliveira, Marcela Tuler Braeken, An Ding, Aaron Yi Pham, Quoc-Viet Distributed, Parallel, and Cluster Computing Artificial Intelligence 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. This article aims to provide a comprehensive resource for researchers and practitioners to navigate and advance the field of verifiable FUL. |
| title | Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00833 |