# FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks

arXiv: https://arxiv.org/abs/2312.04587 · HTML: https://mlsanity.com/paper/2312.04587/

## Key facts

- Cited by 2 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 8 of its 16 references that are in the map.
- First posted on arXiv 4 Dec 2023.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning](https://mlsanity.com/paper/2112.14468/) (2021)
- [A Bayesian Federated Learning Framework with Online Laplace Approximation](https://mlsanity.com/paper/2102.01936/) (2021)
- [Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series](https://mlsanity.com/paper/2101.05639/) (2021)

## Built on by (most cited first, 2 of 2)

- [Trust Aware Federated Learning for Secure Bone Healing Stage Interpretation in e-Health](https://mlsanity.com/paper/2603.06646/) (2026)
- [Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks](https://mlsanity.com/paper/2603.25334/) (2026)

## Abstract (arXiv)

Federated learning has created a decentralized method to train a machine learning model without needing direct access to client data. The main goal of a federated learning architecture is to protect the privacy of each client while still contributing to the training of the global model. However, the main advantage of privacy in federated learning is also the easiest aspect to exploit. Without being able to see the clients' data, it is difficult to determine the quality of the data. By utilizing data poisoning methods, such as backdoor or label-flipping attacks, or by sending manipulated information about their data back to the server, malicious clients are able to corrupt the global model and degrade performance across all clients within a federation. Our novel aggregation method, FedBayes, mitigates the effect of a malicious client by calculating the probabilities of a client's model weights given to the prior model's weights using Bayesian statistics. Our results show that this approach negates the effects of malicious clients and protects the overall federation.