# Defending against Data Poisoning Attacks in Federated Learning via User Elimination

arXiv: https://arxiv.org/abs/2404.12778 · HTML: https://mlsanity.com/paper/2404.12778/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks](https://mlsanity.com/paper/1803.06975/) (2018)
- [Local and Central Differential Privacy for Robustness and Privacy in Federated Learning](https://mlsanity.com/paper/2009.03561/) (2020)
- [From Distributed Machine Learning to Federated Learning: A Survey](https://mlsanity.com/paper/2104.14362/) (2021)
- [Federated Learning Attacks and Defenses: A Survey](https://mlsanity.com/paper/2211.14952/) (2022)
- [Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems](https://mlsanity.com/paper/2011.04065/) (2020)

## Built on by (most cited first, 1 of 1)

- [Secure Cluster-Based Hierarchical Federated Learning in Vehicular Networks](https://mlsanity.com/paper/2505.01186/) (2025)

## Abstract (arXiv)

In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a novel defensive framework focused on the strategic elimination of adversarial users within a federated model. We detect those anomalies in the aggregation phase of the Federated Algorithm, by integrating metadata gathered by the local training instances with Differential Privacy techniques, to ensure that no data leakage is possible. To our knowledge, this is the first proposal in the field of FL that leverages metadata other than the model's gradients in order to ensure honesty in the reported local models. Our extensive experiments demonstrate the efficacy of our methods, significantly mitigating the risk of data poisoning while maintaining user privacy and model performance. Our findings suggest that this new user elimination approach serves us with a great balance between privacy and utility, thus contributing to the arsenal of arguments in favor of the safe adoption of FL in safe domains, both in academic setting and in the industry.