From the viewpoint of physical-layer authentication, spoofing attacks can be foiled by checking channel state information (CSI). Existing CSI-based authentication algorithms mostly require a deep knowledge of the channel variation to deliver decent performance. In this paper, we investigate CSI-based authenticators that can spare the effort to predetermine channel properties by utilizing deep neural networks (DNNs). First, we propose a convolutional neural network (CNN)-enabled authenticator that is able to extract the local features in CSI. Next, the recurrent neural network (RNN) is employed to capture the dependencies between different frequencies in CSI. In addition, we propose to use the convolutional recurrent neural network (CRNN)-a combination of the CNN and the RNN-to learn local and contextual information in CSI for user authentication. Finally, experiments based on Universal Software Radio Peripherals (USRPs) are conducted to demonstrate the performance of the proposed methods on realworld channel estimates. According to the experimental results, the proposed DNNs-enabled schemes can significantly outperform the dynamic time warping (DTW) technique and a heuristic Neyman-Pearson (NP) test in the aspects of false alarm and miss detection. Besides, the hybrid of the CNN and the RNN can further promote the authentication accuracy.

No abstract