# Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning

arXiv: https://arxiv.org/abs/2304.10638 · HTML: https://mlsanity.com/paper/2304.10638/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 71 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Attack of the Tails: Yes, You Really Can Backdoor Federated Learning](https://mlsanity.com/paper/2007.05084/) (2020)
- [Can You Really Backdoor Federated Learning?](https://mlsanity.com/paper/1911.07963/) (2019)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [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)
- [Neurotoxin: Durable Backdoors in Federated Learning](https://mlsanity.com/paper/2206.10341/) (2022)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [Defending against Backdoors in Federated Learning with Robust Learning Rate](https://mlsanity.com/paper/2007.03767/) (2020)

## Built on by (most cited first, 13 of 13)

- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024)
- [Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity](https://mlsanity.com/paper/2405.17462/) (2024)
- [Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure](https://mlsanity.com/paper/2410.10922/) (2024)
- [Identify Backdoored Model in Federated Learning via Individual Unlearning](https://mlsanity.com/paper/2411.01040/) (2024)
- [FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher](https://mlsanity.com/paper/2408.07587/) (2024)
- [Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack](https://mlsanity.com/paper/2411.16167/) (2024)
- [DROP: Poison Dilution via Knowledge Distillation for Federated Learning](https://mlsanity.com/paper/2502.07011/) (2025)
- [Fully Decentralized Certified Unlearning](https://mlsanity.com/paper/2512.08443/) (2025)
- [Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement](https://mlsanity.com/paper/2604.04030/) (2026)
- [A Survey on Federated Unlearning: Challenges and Opportunities](https://mlsanity.com/paper/2403.02437/) (2024)
- [Upcycling Noise for Federated Unlearning](https://mlsanity.com/paper/2412.05529/) (2024)
- [DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems](https://mlsanity.com/paper/2506.01777/) (2025)

## Abstract (arXiv)

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to backdoor attacks. In these attacks, adversaries inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures to penalize the adversaries. Therefore, this paper proposes a methodology that enables adversaries to effectively remove backdoors from the centralized model upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of machine unlearning and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making the adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work that explores machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering image classification scenarios demonstrates the efficacy of the proposed method in efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.