Weak-Jamming Detection in IEEE 802.11 Networks: Techniques, Scenarios and Mobility

TL;DR

This work tackles early detection of weak jamming in IEEE 802.11 networks by transforming PHY-layer IQ samples into image representations and applying deep learning classifiers. It introduces two operational modes—CNN-based binary classification and Sparse Autoencoder-based anomaly detection—and validates them through extensive real-world experiments across indoor, outdoor multipath, and outdoor minimal-multipath environments with a public dataset. The authors extend prior weak-jamming approaches to real-world WiFi-like modulation (OFDM with BPSK/QPSK/16-QAM/64-QAM), demonstrate robust detection under varying distances, mobility, and jamming types, and provide a detailed overhead analysis. The results support the feasibility and practical value of proactive jamming awareness for rapid mitigation, with open data to spur further research and deployment considerations for constrained devices.

Abstract

State-of-the-art solutions detect jamming attacks ex-post, i.e., only when jamming has already disrupted the wireless communication link. In many scenarios, e.g., mobile networks or static deployments distributed over a large geographical area, it is often desired to detect jamming at the early stage, when it affects the communication link enough to be detected but not sufficiently to disrupt it (detection of weak jamming signals). Under such assumptions, devices can enhance situational awareness and promptly apply mitigation, e.g., moving away from the jammed area in mobile scenarios or changing communication frequency in static deployments, before jamming fully disrupts the communication link. Although some contributions recently demonstrated the feasibility of detecting low-power and weak jamming signals, they make simplistic assumptions far from real-world deployments. Given the current state of the art, no evidence exists that detection of weak jamming can be considered with real-world communication technologies. In this paper, we provide and comprehensively analyze new general-purpose strategies for detecting weak jamming signals, compatible by design with one of the most relevant communication technologies used by commercial-off-the-shelf devices, i.e., IEEE 802.11. We describe two operational modes: (i) binary classification via Convolutional Neural Networks and (ii) one-class classification via Sparse Autoencoders. We evaluate and compare the proposed approaches with the current state-of-the-art using data collected through an extensive real-world experimental campaign in three relevant environments. At the same time, we made the dataset available to the public. Our results demonstrate that detecting weak jamming signals is feasible in all considered real-world environments, and we provide an in-depth analysis considering different techniques, scenarios, and mobility patterns.

Figures (24)

• Figure 1: IQ constellations for BPSK, QPSK, 16-QAM and 64-QAM, respectively, obtained from our experiments.
• Figure 2: System and Adversary Model. Our solution applies to two reference scenarios. (a) A receiver (RX) moves from area $A_3$ to area $A_2$ and eventually to $A_1$. RX can receive messages from TX when in $A_2$ and $A_3$, while reception is not possible in $A_1$ due to jamming. (b) A dense network is partially jammed (black devices in $A1$) while (yellow and green) devices in $A_2$ and $A_3$ can communicate.
• Figure 3: We collect the IQ data through a SDR, then divide them into chunks of $n$ samples per image, represent them in a constellation diagram, compute a bi-variate histogram, and store it as an image.
• Figure 4: Visual representation of a the CNN used for binary jamming detection.
• Figure 5: Visual representation of the AE-based jamming detection architecture.