Strengthening Network Intrusion Detection in IoT Environments with Self-Supervised Learning and Few Shot Learning

TL;DR

This paper presents a novel IoT intrusion detection method combining self-supervised learning, few shot learning, and random forests to effectively detect rare and new cyber attacks with high accuracy from limited data.

Contribution

It introduces a new approach integrating SSL, FSL, and RF for improved detection of underrepresented IoT cyber attacks using limited labeled data.

Findings

Achieved over 98.6% accuracy on two IoT datasets.

Outperformed existing methods in detecting rare attacks.

Demonstrated robustness with high precision and recall.

Abstract

The Internet of Things (IoT) has been introduced as a breakthrough technology that integrates intelligence into everyday objects, enabling high levels of connectivity between them. As the IoT networks grow and expand, they become more susceptible to cybersecurity attacks. A significant challenge in current intrusion detection systems for IoT includes handling imbalanced datasets where labeled data are scarce, particularly for new and rare types of cyber attacks. Existing literature often fails to detect such underrepresented attack classes. This paper introduces a novel intrusion detection approach designed to address these challenges. By integrating Self Supervised Learning (SSL), Few Shot Learning (FSL), and Random Forest (RF), our approach excels in learning from limited and imbalanced data and enhancing detection capabilities. The approach starts with a Deep Infomax model trained to extract key features from the dataset. These features are then fed into a prototypical network to generate discriminate embedding. Subsequently, an RF classifier is employed to detect and classify potential malware, including a range of attacks that are frequently observed in IoT networks. The proposed approach was evaluated through two different datasets, MaleVis and WSN-DS, which demonstrate its superior performance with accuracies of 98.60% and 99.56%, precisions of 98.79% and 99.56%, recalls of 98.60% and 99.56%, and F1-scores of 98.63% and 99.56%, respectively.