# Detection and Prevention Against Poisoning Attacks in Federated Learning

arXiv: https://arxiv.org/abs/2210.14944 · HTML: https://mlsanity.com/paper/2210.14944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 24 Oct 2022.

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

- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Deep Federated Learning for Autonomous Driving](https://mlsanity.com/paper/2110.05754/) (2021)
- [Federated Learning in Vehicular Networks](https://mlsanity.com/paper/2006.01412/) (2020)
- [FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations](https://mlsanity.com/paper/2202.01267/) (2022)
- [On-Board Federated Learning for Dense LEO Constellations](https://mlsanity.com/paper/2111.12769/) (2021)
- [Evaluating Federated Learning for Intrusion Detection in Internet of Things: Review and Challenges](https://mlsanity.com/paper/2108.00974/) (2021)
- [Cybersecurity Threats in Connected and Automated Vehicles based Federated Learning Systems](https://mlsanity.com/paper/2102.13256/) (2021)

## Abstract (arXiv)

This paper proposes and investigates a new approach for detecting and preventing several different types of poisoning attacks from affecting a centralized Federated Learning model via average accuracy deviation detection (AADD). By comparing each client's accuracy to all clients' average accuracy, AADD detect clients with an accuracy deviation. The implementation is further able to blacklist clients that are considered poisoned, securing the global model from being affected by the poisoned nodes. The proposed implementation shows promising results in detecting poisoned clients and preventing the global model's accuracy from deteriorating.