Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

TLDR

Machine‑learning–based intrusion detection is essential for IoT, yet most approaches are centralized, prompting interest in federated learning, which remains under‑explored for IoT IDS. This study evaluates a federated‑learning IDS that uses a multiclass classifier to detect attacks under varying data distributions in an IoT setting. The authors partition the ToN_IoT dataset by device IP and attack type into three settings and test different aggregation functions within the IBMFL framework. The evaluation reveals several challenges and suggests future research directions for deploying federated‑learning IDS in real‑world IoT environments.

Abstract

The application of Machine Learning (ML) techniques to the well-known intrusion detection systems (IDS) is key to cope with increasingly sophisticated cybersecurity attacks through an effective and efficient detection process. In the context of the Internet of Things (IoT), most ML-enabled IDS approaches use centralized approaches where IoT devices share their data with data centers for further analysis. To mitigate privacy concerns associated with centralized approaches, in recent years the use of Federated Learning (FL) has attracted a significant interest in different sectors, including healthcare and transport systems. However, the development of FL-enabled IDS for IoT is in its infancy, and still requires research efforts from various areas, in order to identify the main challenges for the deployment in real-world scenarios. In this direction, our work evaluates a FL-enabled IDS approach based on a multiclass classifier considering different data distributions for the detection of different attacks in an IoT scenario. In particular, we use three different settings that are obtained by partitioning the recent ToN_IoT dataset according to IoT devices’ IP address and types of attack. Furthermore, we evaluate the impact of different aggregation functions according to such setting by using the recent IBMFL framework as FL implementation. Additionally, we identify a set of challenges and future directions based on the existing literature and the analysis of our evaluation results.