通过深度学习进行窄带干扰检测
Narrowband Interference Detection via Deep Learning
摘要：
由于无线设备的指数增长导致的频谱使用的增加，检测和避免干扰已经成为确保不间断无线通信的日益相关的问题。在本文中，我们把我们的兴趣集中在检测窄带干扰所造成的信号，尽管占用频谱的一小部分，但只会对无线系统造成重大损害，例如，在干扰导频和其他信号的情况下，用于均衡信道的影响或实现同步。由于这些信号的尺寸很小，由于它们的低能量足迹，检测可能很困难，同时极大地影响（或在某些情况下完全拒绝）网络通信。我们提出了一种新的窄带干扰检测解决方案，利用卷积神经网络（CNN）来检测和定位这些信号的高精度。为了证明我们解决方案的有效性，我们构建了一个原型，该原型已在现实世界的空中大规模无线测试平台上进行了测试和验证。我们的实验结果表明，我们的解决方案是能够检测窄带干扰攻击的准确率高达99%。此外，它还能够检测到同时影响多个频率的多个攻击，即使是以前看不见的攻击模式。我们的解决方案不仅可以实现92%到99%之间的检测精度，而且只增加了0.093ms的推理延迟。
英文摘要：
Due to the increased usage of spectrum caused by the exponential growth of wireless devices, detecting and avoiding interference has become an increasingly relevant problem to ensure uninterrupted wireless communications. In this paper, we focus our interest on detecting narrowband interference caused by signals that despite occupying a small portion of the spectrum only can cause significant harm to wireless systems, for example, in the case of interference with pilots and other signals that are used to equalize the effect of the channel or attain synchronization. Due to the small sizes of these signals, detection can be difficult due to their low energy footprint, while greatly impacting (or denying completely in some cases) network communications. We present a novel narrowband interference detection solution that utilizes convolutional neural networks (CNNs) to detect and locate these signals with high accuracy. To demonstrate the effectiveness of our solution, we have built a prototype that has been tested and validated on a real-world over-the-air large-scale wireless testbed. Our experimental results show that our solution is capable of detecting narrowband jamming attacks with an accuracy of up to 99%. Moreover, it is also able to detect multiple attacks affecting several frequencies at the same time even in the case of previously unseen attack patterns. Not only can our solution achieve a detection accuracy between 92% and 99%, but it does so by only adding an inference latency of 0.093ms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
