Early Jamming Detection in Mobile Indoor Scenarios via Deep Learning

The current state of the art on jamming detection relies on link-layer metrics. A few examples are the bit-error rate, the packet delivery ratio, the throughput, and the increase of the signal-to-noise ratio. As a result, these techniques can only detect jamming ex-post, i.e., once the attack has already taken down the communication link. These solutions are unfit in mobile scenarios, e.g., drones, which might lose the link to the remote controller, being unable to predict the attack. Our solution is rooted in the idea that a drone flying against a jammed area is experiencing an increasing effect of the jamming. Therefore, drones might use this phenomenon to detect jamming early, i.e., before it completely disrupts the communication link. Such an approach would allow drones and possibly their pilots to make an informed decision and maintain full control of the navigation, providing security and safety. In this paper, we propose Bloodhound+, a solution for early jamming detection on mobile devices. Our approach analyzes raw physical-layer information (I-Q samples) acquired from the channel. We assemble this information into grayscale images, and we use sparse autoencoders to detect image anomalies caused by jamming attacks. To test our solution against a wide set of configurations, we acquired a large dataset of indoor measurements using multiple hardware, jamming strategies, and communication parameters. Our results indicate that Bloodhound+ can detect indoor jamming up to 20 meters away from the jamming source at the minimum available relative jamming power, with a minimum accuracy of 99.7%. Our solution is also robust to various sampling rates adopted by the jammer, as well as to the type of signal used for jamming.