LocKedge: Low-Complexity Cyberattack Detection in IoT Edge Computing

TL;DR

LocKedge introduces a low-complexity, edge-based cyberattack detection system for IoT networks that achieves high accuracy and quick response by operating near attack sources, using centralized and federated learning methods.

Contribution

The paper presents a novel low-complexity detection mechanism deployed at the IoT edge, outperforming existing machine learning methods in accuracy and complexity.

Findings

LocKedge outperforms NN, CNN, RNN, KNN, SVM, RF, Decision Tree in accuracy.

LocKedge has lower complexity than neural network-based methods.

The architecture is effective in both centralized and federated learning settings.

Abstract

Internet of Things and its applications are becoming commonplace with more devices, but always at risk of network security. It is therefore crucial for an IoT network design to identify attackers accurately, quickly and promptly. Many solutions have been proposed, mainly concerning secure IoT architectures and classification algorithms, but none of them have paid enough attention to reducing the complexity. Our proposal in this paper is an edge cloud architecture that fulfills the detection task right at the edge layer, near the source of the attacks for quick response, versatility, as well as reducing the workload of the cloud. We also propose a multi attack detection mechanism called LocKedge Low Complexity Cyberattack Detection in IoT Edge Computing, which has low complexity for deployment at the edge zone while still maintaining high accuracy. LocKedge is implemented in two manners: centralized and federated learning manners in order to verify the performance of the architecture from different perspectives. The performance of our proposed mechanism is compared with that of other machine learning and deep learning methods using the most updated BoT IoT data set. The results show that LocKedge outperforms other algorithms such as NN, CNN, RNN, KNN, SVM, KNN, RF and Decision Tree in terms of accuracy and NN in terms of complexity.