# Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning

arXiv: https://arxiv.org/abs/2504.01705 · HTML: https://mlsanity.com/paper/2504.01705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 9 of 9)

- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [Dissecting Language Models: Machine Unlearning via Selective Pruning](https://mlsanity.com/paper/2403.01267/) (2024)
- [Decentralized Federated Learning: A Survey on Security and Privacy](https://mlsanity.com/paper/2401.17319/) (2024)
- [Unlearning during Learning: An Efficient Federated Machine Unlearning Method](https://mlsanity.com/paper/2405.15474/) (2024)
- [Exploring Jamming and Hijacking Attacks for Micro Aerial Drones](https://mlsanity.com/paper/2403.03858/) (2024)

## Abstract (arXiv)

The Internet of Drones (IoD), where drones collaborate in data collection and analysis, has become essential for applications such as surveillance and environmental monitoring. Federated learning (FL) enables drones to train machine learning models in a decentralized manner while preserving data privacy. However, FL in IoD networks is susceptible to attacks like data poisoning and model inversion. Federated unlearning (FU) mitigates these risks by eliminating adversarial data contributions, preventing their influence on the model. This paper proposes sky of unlearning (SoUL), a federated unlearning framework that efficiently removes the influence of unlearned data while maintaining model performance. A selective pruning algorithm is designed to identify and remove neurons influential in unlearning but minimally impact the overall performance of the model. Simulations demonstrate that SoUL outperforms existing unlearning methods, achieves accuracy comparable to full retraining, and reduces computation and communication overhead, making it a scalable and efficient solution for resource-constrained IoD networks.