Securing Federated Learning in IoT: A Survey of Attacks, Defenses, and Frameworks
- 20 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (22) , 47163-47190
Abstract
Federated learning (FL) is a powerful machine learning (ML) technique that allows multiple clients to collaborate on training models while keeping their data private. Unlike traditional centralized methods, FL ensures that data are kept separate, which helps to protect privacy. However, an important area that needs more research while using the FL system is detecting harmful models within the Internet of Things (IoT) context. For example, poisoning attacks, where compromised clients introduce harmful data, can degrade the model’s overall performance or lead to incorrect predictions. This article comprehensively reviews of recent attacks in FL within IoT networks, along with defense mechanisms and common FL frameworks. It begins by highlighting the significance of FL in IoT networks, exploring its applications, benefits, and inherent security challenges. It then explores specific attacks targeting FL in IoT networks. The defensive strategies are evaluated, including their performance metrics, datasets used, and related work, providing a comparative analysis of these techniques. Common FL frameworks and their criteria are reviewed. Our goal is to offer a detailed understanding and solutions to enhance the strength and resilience of FL systems in IoT networks.Keywords
All Related Versions
This publication has 113 references indexed in Scilit:
- Fake or Compromised? Making Sense of Malicious Clients in Federated Learning2024
- Federated Learning Using Tensor Flow2022
- CONTRA: Defending Against Poisoning Attacks in Federated Learning2021
- Threats to Federated Learning2020
- Data Poisoning Attacks Against Federated Learning Systems2020
- Detecting and mitigating poisoning attacks in federated learning using generative adversarial networksConcurrency and Computation: Practice and Experience, 2020
- Multi-institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation2019
- Domain-Adversarial Training of Neural Networks2017
- Calibrating Noise to Sensitivity in Private Data Analysis2006
- Multiparty Computation from Threshold Homomorphic Encryption2001