FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters
On the map: LLM safety and security → Federated unlearning and poisoning
Abstract (arXiv)
Federated unlearning (FU) is critical for complying with legal mandates like the right to be forgotten in decentralized systems, yet current methods face a persistent dilemma between non-target knowledge loss and high request latency. To resolve these issues, we propose FedUP, a one-shot federated unlearning framework utilizing lightweight pluggable filters that act as a "knowledge funnel" to screen out target data while preserving original model performance. By freezing original model parameters and training filters at the server side using differentially private (DP)-protected class centroid samples, FedUP bypasses the need for multi-round client-server communication and complex retraining, reducing unlearning latency from minutes to mere seconds. Additionally, the framework's pluggable architecture ensures inherent reversibility, enabling the seamless restoration of forgotten knowledge by simply removing the filters. Extensive experiments on diverse image and text tasks demonstrate that FedUP effectively reduces non-target knowledge loss and achieves superior unlearning precision and efficiency across various scenarios. Code is available at: https://github.com/suows/FedUP-code.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 30 of its 47 references that are in the map. First posted on arXiv 23 Jun 2026.
Builds on
30 of 47 references.
Closest ancestors · 9
Same direction, newest first
- 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter28 Feb
- 2024Federated Unlearning with Gradient Descent and Conflict Mitigation28 Dec
- 2024Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging2 Jul
- 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
- 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning4 Feb
- 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
- 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
- 2022Federated Unlearning with Knowledge Distillation24 Jan
- 2021Federated Unlearning via Class-Discriminative Pruning22 Oct
Other references · 21
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
- 2019Machine Unlearningcited by 1,020
- 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2019Certified Data Removal from Machine Learning Modelscited by 512
- 2020Amnesiac Machine Learningcited by 305
- 2022A Survey of Machine Unlearningcited by 298
9 more
- 2021Adaptive Machine Unlearningcited by 164
- 2021Graph Unlearningcited by 129
- 2020Learn to Forget: Machine Unlearning via Neuron Maskingcited by 56
- 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
- 2023Inductive Graph Unlearningcited by 30
- 2024Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospectscited by 28
- 2025Exact Unlearning of Finetuning Data via Model Merging at Scalecited by 14
- 2024Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearningcited by 12
- 2025SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devicescited by 8
Built on by
Not cited yet.