<i>Radar</i> ²: Passive Spy Radar Detection and Localization Using COTS mmWave Radar

Millimeter-wave (mmWave) radars have found applications in a wide range of domains, including human tracking, health monitoring, and autonomous driving, for their unobtrusive nature high accuracy. These capabilities, however, if used malicious purposes, could also result serious security privacy issues. For example, user's daily life be secretly monitored by spy radar. Hence, there is strong urge to develop systems that can detect locate such radars. In this paper, we propose $Radar^2$, practical system passive radar detection localization using single commercial off-the-shelf (COTS) mmWave Specifically, novel \textit{Frequency Component Detection} method the existence signals, distinguish between WiGig signals waveform classifier based on convolutional neural network (CNN), localize triangulation detector's observations at multiple anchor points. Not only does $Radar^2$ work different types radar, but it simultaneously. Finally, performed extensive experiments evaluate effectiveness robustness various settings. Our evaluation results show rate above 96$\%$ error within 0.3m. The reveal robust against environmental factors (e.g., room layout activities).