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.

翻译：目前干扰检测领域的先进技术依赖于链路层指标，例如误码率、数据包投递率、吞吐量和信噪比提升等。因此，这些技术只能进行事后干扰检测，即攻击已经破坏通信链路后才被发现。这种解决方案不适用于移动场景（如无人机），因为无人机可能失去与远程控制器的链路连接，无法预测攻击。我们的方案基于以下核心理念：当无人机飞越受干扰区域时，会感受到干扰效应的逐步增强。因此，无人机可利用这一现象在干扰完全破坏通信链路前实现早期检测。这种方法能让无人机及其操控者做出明智决策，保持对导航的完全控制，从而提升安全性与可靠性。本文提出Bloodhound+方案，这是一种用于移动设备早期干扰检测的解决方案。该方法分析从信道获取的原始物理层信息（I-Q样本），将数据组装为灰度图像，并采用稀疏自编码器检测干扰攻击导致的图像异常。为测试方案在多种配置下的表现，我们使用多套硬件设备、干扰策略和通信参数采集了大规模室内测量数据集。结果表明，在最小可用相对干扰功率下，Bloodhound+可在距干扰源20米范围内检测室内干扰，最低准确率达99.7%。该方案对干扰机采用的采样速率及干扰信号类型均具有鲁棒性。