Training-free intrusion detection using channel state information of Wi-Fi signals

With the rapid development of wireless communication technology, Wi-Fi has been widely used in public and private fields. The wireless device-free passive human detection technology has broad application prospects in the field of home automation. Considering that the existing solutions are difficult to explain the huge performance differences in different scenarios, this paper introduces a training-free intrusion detection using channel state information of Wi-Fi signals, Which exploits the fine-grained channel state information (CSI) on Wi-Fi devices to capture the minor variations caused by human movement. To amplify such variations, the multiple signal classification algorithm (MUSIC) is used to decompose the covariance matrix of the CSI time series, and the orthogonality of the signal angular velocity vector and the noise subspace is used to extract the path change speed. and by calculating the phase difference of the corresponding path judges the intrusion detection We implemented our human detection method in two typical indoor environments (i.e., a meeting room and a laboratory) and the results demonstrate an average false positive (FP) of 1.07% and an average false negative (FN) of 1.87%. The experimental results show that the proposed method can effectively eliminate the influence of environmental changes on detection accuracy and improves the robustness of the system.