# Federated unlearning and poisoning

Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/federated-unlearning-and-poisoning/

## Key facts

- Federated unlearning and poisoning: 213 papers on arXiv since 2021 (data through 14 Oct 2026).
- 52 of its 213 mapped papers (24%) cite “The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining” (2022, arXiv 2203.07320).
- 45 of its 213 mapped papers (21%) cite “Federated Unlearning: How to Efficiently Erase a Client in FL?” (2022, arXiv 2207.05521).
- 2 new papers 24 Sep–14 Oct.

## Most cited here

- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022), cited by 52 papers here
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022), cited by 45 papers here
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021), cited by 43 papers here
- [Federated Unlearning with Knowledge Distillation](https://mlsanity.com/paper/2201.09441/) (2022), cited by 36 papers here
- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023), cited by 35 papers here
- [VeriFi: Towards Verifiable Federated Unlearning](https://mlsanity.com/paper/2205.12709/) (2022), cited by 28 papers here
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024), cited by 17 papers here
- [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://mlsanity.com/paper/2302.02069/) (2023), cited by 14 papers here
- [Federated Unlearning with Gradient Descent and Conflict Mitigation](https://mlsanity.com/paper/2412.20200/) (2024), cited by 13 papers here
- [Unlearning during Learning: An Efficient Federated Machine Unlearning Method](https://mlsanity.com/paper/2405.15474/) (2024), cited by 12 papers here

## New (24 Sep–14 Oct)

- [FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation](https://mlsanity.com/paper/2610.18430/) (2026-10-13)
- [Machine Unlearning for Federated Socially Fair k-Means Clustering](https://mlsanity.com/paper/2610.13717/) (2026-10-09)