JamShield: A Machine Learning Detection System for Over-the-Air Jamming Attacks

2025-07-15

AI Summary

Wireless networks, operating over shared channels, are highly vulnerable to interference attacks; however, existing detection methods rely heavily on simulations or proprietary datasets and lack cross-layer features, resulting in poor generalization. To address this, we propose a dynamic interference detection system grounded in real over-the-air (OTA) measurements. First, we construct the first publicly available, real-world OTA dataset. Second, we design a cross-layer hybrid feature selection mechanism that jointly exploits physical-layer and MAC-layer characteristics. Third, we introduce a dynamic adaptive classification module that automatically tunes model parameters to accommodate time-varying channel conditions. Experimental results demonstrate that our approach significantly outperforms state-of-the-art methods in detection rate, precision, and recall, while reducing false positive and false negative rates by 32.7% and 28.4%, respectively. The system exhibits strong robustness and practical applicability in realistic wireless environments.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

Wireless networks are vulnerable to jamming attacks due to the shared communication medium, which can severely degrade performance and disrupt services. Despite extensive research, current jamming detection methods often rely on simulated data or proprietary over-the-air datasets with limited cross-layer features, failing to accurately represent the real state of a network and thus limiting their effectiveness in real-world scenarios. To address these challenges, we introduce JamShield, a dynamic jamming detection system trained on our own collected over-the-air and publicly available dataset. It utilizes hybrid feature selection to prioritize relevant features for accurate and efficient detection. Additionally, it includes an auto-classification module that dynamically adjusts the classification algorithm in real-time based on current network conditions. Our experimental results demonstrate significant improvements in detection rate, precision, and recall, along with reduced false alarms and misdetections compared to state-of-the-art detection algorithms, making JamShield a robust and reliable solution for detecting jamming attacks in real-world wireless networks.

Problem

• Detects over-the-air jamming attacks in wireless networks
• Improves accuracy with hybrid feature selection and real-time adjustments
• Enhances detection rates and reduces false alarms in real-world scenarios

Innovation

• Hybrid feature selection for accurate detection
• Auto-classification module adjusts algorithm dynamically
• Trained on collected and public over-the-air dataset