FedMicro-IDA: A Federated Learning and Microservices-based Framework for IoT Data Analytics

TL;DR

This paper introduces FedMicro-IDA, a federated learning framework built on microservices architecture for IoT data analytics, enhancing privacy, reducing latency, and improving malware detection accuracy.

Contribution

It proposes a novel microservices-based federated learning architecture tailored for IoT, validated through malware detection experiments with superior performance.

Findings

Achieved 99.24% detection accuracy.

Outperformed existing methods in malware classification.

Reduced latency and bandwidth usage in IoT analytics.

Abstract

The Internet of Things (IoT) has recently proliferated in both size and complexity. Using multi-source and heterogeneous IoT data aids in providing efficient data analytics for a variety of prevalent and crucial applications. To address the privacy and security concerns raised by analyzing IoT data locally or in the cloud, distributed data analytics techniques were proposed to collect and analyze data in edge or fog devices. In this context, federated learning has been recommended as an ideal distributed machine/deep learning-based technique for edge/fog computing environments. Additionally, the data analytics results are time-sensitive; they should be generated with minimal latency and high reliability. As a result, reusing efficient architectures validated through a high number of challenging test cases would be advantageous. The work proposed here presents a solution using a microservices-based architecture that allows an IoT application to be structured as a collection of fine-grained, loosely coupled, and reusable entities. The proposed solution uses the promising capabilities of federated learning to provide intelligent microservices that ensure efficient, flexible, and extensible data analytics. This solution aims to deliver cloud calculations to the edge to reduce latency and bandwidth congestion while protecting the privacy of exchanged data. The proposed approach was validated through an IoT-malware detection and classification use case. MaleVis, a publicly available dataset, was used in the experiments to analyze and validate the proposed approach. This dataset included more than 14,000 RGB-converted images, comprising 25 malware classes and one benign class. The results showed that our proposed approach outperformed existing state-of-the-art methods in terms of detection and classification performance, with a 99.24%.