Enhancing IoT Intrusion Detection Systems through Adversarial Training

TL;DR

This paper presents a robust IoT intrusion detection system that uses adversarial training with FGSM attacks and XGBoost to improve detection accuracy against complex cyber threats, demonstrating high performance on the NF-ToN-IoT v2 dataset.

Contribution

It introduces an adversarial training approach combining FGSM attacks and XGBoost for IoT intrusion detection, enhancing robustness against evolving threats.

Findings

Achieved 95.3% accuracy on clean data

Achieved 94.5% accuracy on adversarial data

Demonstrated effectiveness against complex attack scenarios

Abstract

The augmentation of Internet of Things (IoT) devices transformed both automation and connectivity but revealed major security vulnerabilities in networks. We address these challenges by designing a robust intrusion detection system (IDS) to detect complex attacks by learning patterns from the NF-ToN-IoT v2 dataset. Intrusion detection has a realistic testbed through the dataset's rich and high-dimensional features. We combine distributed preprocessing to manage the dataset size with Fast Gradient Sign Method (FGSM) adversarial attacks to mimic actual attack scenarios and XGBoost model adversarial training for improved system robustness. Our system achieves 95.3% accuracy on clean data and 94.5% accuracy on adversarial data to show its effectiveness against complex threats. Adversarial training demonstrates its potential to strengthen IDS against evolving cyber threats and sets the foundation for future studies. Real-time IoT environments represent a future deployment opportunity for these systems, while extensions to detect emerging threats and zero-day vulnerabilities would enhance their utility.