SoK: Challenges and Opportunities in Federated Unlearning

H Jeong, S Ma, A Houmansadr - arXiv preprint arXiv:2403.02437, 2024 - arxiv.org
… unique complexities of federated unlearning, highlighting limitations on directly applying
centralized unlearning methods. We compare existing federated unlearning methods regarding …

A survey on federated unlearning: Challenges, methods, and future directions

Z Liu, Y Jiang, J Shen, M Peng, KY Lam… - ACM Computing …, 2023 - dl.acm.org
… 2 Targets and Challenges of Federated Unlearning … explore the targets of federated
unlearning and the associated challenges compared to traditional machine unlearning. The insights …

Federated unlearning: A survey on methods, design guidelines, and evaluation metrics

N Romandini, A Mora, C Mazzocca… - arXiv preprint arXiv …, 2024 - arxiv.org
… Finally, we outline the most relevant and still open technical challenges, by identifying the …
, ie just excluding the client that requested its removal from the federation, we performed a set …

Towards Federated Domain Unlearning: Verification Methodologies and Challenges

K Tam, K Xu, L Li, H Fu - arXiv preprint arXiv:2406.03078, 2024 - arxiv.org
federated unlearning present significant challenges in the context of federated domain
unlearning… methods for federated unlearning introduce substantial challenges within the sphere of …

VeriFi: Towards Verifiable Federated Unlearning

X Gao, X Ma, J Wang, Y Sun, B Li, S Ji… - … on Dependable and …, 2024 - ieeexplore.ieee.org
… not be a panacea for all the challenges faced by federated unlearning and verification, they
… rich set of research opportunities to explore further, such as new unlearning and verification …

Federated Learning with Blockchain-Enhanced Machine Unlearning: A Trustworthy Approach

X Zuo, M Wang, T Zhu, L Zhang, S Yu… - arXiv preprint arXiv …, 2024 - arxiv.org
… oracle to remove the influence of their data, with little opportunity to verify it [7]. This makes
… This research addresses the challenge of integrating machine unlearning into Federated

Machine unlearning: Solutions and challenges

J Xu, Z Wu, C Wang, X Jia - IEEE Transactions on Emerging …, 2024 - ieeexplore.ieee.org
… promising progress while revealing key challenges and opportunities for improvement. The
… to facilitate unlearning. When the federated unlearning process begins, the federated server …

A survey of federated unlearning: A taxonomy, challenges and future directions

J Yang, Y Zhao - arXiv preprint arXiv:2310.19218, 2023 - arxiv.org
… For example, an honest-but-curious server or adversarial clients, the discrepancy between
the global model versions before and after unlearning presents an opportunity to extract …

Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging

Z Deng, L Luo, H Chen - arXiv preprint arXiv:2407.02356, 2024 - arxiv.org
challenge in federated learning (FL), leading to the development of federated unlearning
(FU)… to guarantee a higher level forgetting, marking an opportunity for innovation in unlearning. …

Threats, attacks, and defenses in machine unlearning: A survey

Z Liu, H Ye, C Chen, KY Lam - arXiv preprint arXiv:2403.13682, 2024 - arxiv.org
… the unlearning phase, requesting users have the opportunity … uses of federated unlearning
compared to traditional unlearning … Lastly, this work identifies challenges and outlines future …