Enhancing IoT Intrusion Detection Systems through Adversarial Training

2025-07-25

AI Summary

To address widespread security vulnerabilities in Internet of Things (IoT) devices, this paper proposes a lightweight intrusion detection system (IDS) based on adversarial training. Methodologically, it introduces the Fast Gradient Sign Method (FGSM) into IoT intrusion detection for the first time, integrating high-dimensional network flow features from the NF-ToN-IoT v2 dataset within a distributed preprocessing and adversarial sample generation framework, and employs XGBoost as the base classifier for adversarial training. The key contribution lies in adapting the FGSM mechanism to IoT traffic characteristics, enabling effective modeling and robust detection of complex, stealthy attacks. Experimental results demonstrate that the model achieves 95.3% accuracy on clean test data and maintains 94.5% accuracy under adversarial perturbations—significantly outperforming baseline methods—thereby validating its superior robustness and practical applicability for real-world IoT security.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

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.

Problem

• Enhancing IoT security against complex cyber threats
• Improving intrusion detection system robustness via adversarial training
• Addressing IoT vulnerabilities with high-accuracy attack detection

Innovation

• Adversarial training with FGSM for robust IDS
• XGBoost model enhances detection accuracy
• Distributed preprocessing handles large dataset