AR2FL: Anomaly-Resistant Robust Framework for Federated Learning
- 25 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (2) , 1131-1142
Abstract
Federated Learning (FL) enables collaborative model training across decentralized data sources while preserving privacy. However, FL systems are vulnerable to attacks from malicious clients that can degrade model performance and compromise integrity. In this work, we propose AR2FL, an anomaly-resistant and robust framework that enhances FL aggregation by leveraging mean latent representations of client updates. This data-driven approach enables the server to estimate inter-client similarity and dynamically scale clients contributions, reducing the influence of anomalous or adversarial updates. Unlike methods based on fixed distance metrics such as cosine similarity or Euclidean distance, AR2FL captures deeper statistical patterns in the latent space, enabling more accurate and secure model updates. Experiments on several datasets show AR2FL maintains strong accuracy, fast convergence, and high robustness, making it suitable for secure large-scale FL.Keywords
This publication has 15 references indexed in Scilit:
- FLAME: Federated Learning With Masked Autoencoders and Mean-Prototypes Embedding for Sparsely Labeled Medical ImagesIEEE Transactions on Emerging Topics in Computational Intelligence, 2025
- Online Fault Diagnosis of Industrial Robot Using IoRT and Hybrid Deep Learning Techniques: An Experimental ApproachIEEE Internet of Things Journal, 2024
- TDFL: Truth Discovery Based Byzantine Robust Federated LearningIEEE Transactions on Parallel and Distributed Systems, 2022
- AdaFed: Optimizing Participation-Aware Federated Learning With Adaptive Aggregation WeightsIEEE Transactions on Network Science and Engineering, 2022
- CONTRA: Defending Against Poisoning Attacks in Federated Learning2021
- Hierarchical Federated Learning ACROSS Heterogeneous Cellular Networks2020
- Federated Learning With Differential Privacy: Algorithms and Performance AnalysisIEEE Transactions on Information Forensics and Security, 2020
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning2019
- Practical Secure Aggregation for Privacy-Preserving Machine Learning2017
- Privacy-Preserving Deep Learning2015