# Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

arXiv: https://arxiv.org/abs/2202.06414 · HTML: https://mlsanity.com/paper/2202.06414/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2022.

## Built on by (most cited first, 5 of 5)

- [Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2210.09305/) (2022)
- [Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing](https://mlsanity.com/paper/2403.13108/) (2024)
- [The poison of dimensionality](https://mlsanity.com/paper/2409.17328/) (2024)
- [Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2506.23583/) (2025)
- [FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning](https://mlsanity.com/paper/2404.11905/) (2024)

## Abstract (arXiv)

Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many security challenges. Among them, model poisoning attacks have a significant impact on the security and performance of FL. Given that there have been many studies focusing on defending against model poisoning attacks, it is necessary to survey the existing work and provide insights to inspire future research. In this paper, we first classify defense mechanisms for model poisoning attacks into two categories: evaluation methods for local model updates and aggregation methods for the global model. Then, we analyze some of the existing defense strategies in detail. We also discuss some potential challenges and future research directions. To the best of our knowledge, we are the first to survey defense methods for model poisoning attacks in FL.