Effective Intrusion Detection in Highly Imbalanced IoT Networks with Lightweight S2CGAN-IDS

TL;DR

This paper introduces a lightweight deep learning framework, S2CGAN-IDS, that improves intrusion detection in highly imbalanced IoT networks by effectively increasing minority class detection without sacrificing overall accuracy.

Contribution

The paper proposes a novel S2CGAN-IDS framework that leverages traffic distribution to enhance minority class detection in imbalanced IoT network data.

Findings

Outperforms existing methods in Precision and Recall.

Achieves a 10.2% improvement in F1-score.

Effectively detects rare attack types in imbalanced datasets.

Abstract

Since the advent of the Internet of Things (IoT), exchanging vast amounts of information has increased the number of security threats in networks. As a result, intrusion detection based on deep learning (DL) has been developed to achieve high throughput and high precision. Unlike general deep learning-based scenarios, IoT networks contain benign traffic far more than abnormal traffic, with some rare attacks. However, most existing studies have been focused on sacrificing the detection rate of the majority class in order to improve the detection rate of the minority class in class-imbalanced IoT networks. Although this way can reduce the false negative rate of minority classes, it both wastes resources and reduces the credibility of the intrusion detection systems. To address this issue, we propose a lightweight framework named S2CGAN-IDS. The proposed framework leverages the distribution characteristics of network traffic to expand the number of minority categories in both data space and feature space, resulting in a substantial increase in the detection rate of minority categories while simultaneously ensuring the detection precision of majority categories. To reduce the impact of sparsity on the experiments, the CICIDS2017 numeric dataset is utilized to demonstrate the effectiveness of the proposed method. The experimental results indicate that our proposed approach outperforms the superior method in both Precision and Recall, particularly with a 10.2% improvement in the F1-score.