mlsanityData to 14 Oct 2026

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

arXiv 2504.01705 ↗First posted 2 Apr 2025cs.LG cs.AI cs.MAcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

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.

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.

Builds on

9 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Method24 May
  2. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
  3. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  4. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 5

  1. 2019Machine Unlearningcited by 1,061
  2. 2023Machine Unlearning: Solutions and Challengescited by 93
  3. 2024Dissecting Language Models: Machine Unlearning via Selective Pruningcited by 42
  4. 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
  5. 2024Exploring Jamming and Hijacking Attacks for Micro Aerial Dronescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Client-Verifiable and Efficient Federated Unlearning in Low-Altitude Wireless Networks
  2. 2024Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
  3. 2026Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
  4. 2025Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-Gradients
  5. 2025FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
  6. 2024Federated Unlearning with Gradient Descent and Conflict Mitigation
  7. 2024FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Method
  8. 2023Exploring Federated Unlearning: Review, Comparison, and Insights