# FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning

arXiv: https://arxiv.org/abs/2603.28673 · HTML: https://mlsanity.com/paper/2603.28673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Black-box Backdoor Defense via Zero-shot Image Purification](https://mlsanity.com/paper/2303.12175/) (2023)
- [Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions](https://mlsanity.com/paper/2303.02213/) (2023)
- [Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges](https://mlsanity.com/paper/2407.06754/) (2024)
- [SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation](https://mlsanity.com/paper/2102.02402/) (2021)
- [FedDefender: Backdoor Attack Defense in Federated Learning](https://mlsanity.com/paper/2307.08672/) (2023)
- [Mitigating Backdoors in Federated Learning with FLD](https://mlsanity.com/paper/2303.00302/) (2023)
- [Federated Learning for Misbehaviour Detection with Variational Autoencoders and Gaussian Mixture Models](https://mlsanity.com/paper/2405.09903/) (2024)
- [FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attacks](https://mlsanity.com/paper/2411.02773/) (2024)
- [Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks](https://mlsanity.com/paper/2502.00587/) (2025)
- [Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis](https://mlsanity.com/paper/2503.04473/) (2025)

## Abstract (arXiv)

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to severe consequences, especially in critical applications such as autonomous driving, healthcare, and finance. Detecting and mitigating backdoor attacks is crucial across the lifespan of model's phases, including pre-training, in-training, and post-training. In this paper, we propose Pre-Training Backdoor Mitigation for Federated Learning (FL-PBM), a novel defense mechanism that proactively filters poisoned data on the client side before model training in a federated learning (FL) environment. The approach consists of three stages: (1) inserting a benign trigger into the data to establish a controlled baseline, (2) applying Principal Component Analysis (PCA) to extract discriminative features and assess the separability of the data, (3) performing Gaussian Mixture Model (GMM) clustering to identify potentially malicious data samples based on their distribution in the PCA-transformed space, and (4) applying a targeted blurring technique to disrupt potential backdoor triggers. Together, these steps ensure that suspicious data is detected early and sanitized effectively, thereby minimizing the influence of backdoor triggers on the global model. Experimental evaluations on image-based datasets demonstrate that FL-PBM reduces attack success rates by up to 95% compared to baseline federated learning (FedAvg) and by 30 to 80% relative to state-of-the-art defenses (RDFL and LPSF). At the same time, it maintains over 90% clean model accuracy in most experiments, achieving better mitigation without degrading model performance.