On the Detection of Replay Authentication Attacks Through Channel State Information Analysis

The reciprocity of channel state information (CSI) observed by two devices communicating wirelessly has been leveraged to develop security solutions for resource-limited IoT devices. Despite considerable research in this area, much of the attention has been on theoretical and simulated analyses. However, the practical implementation of these security solutions faces significant challenges, primarily due to limited hardware capabilities and varying channel conditions. To bridge this research gap, we revisit the assumption of channel reciprocity from an experimental perspective. Our experimental investigations uncover a notable decline in channel reciprocity for low-cost devices due to the variability in channel conditions and the asynchronous nature of CSI measurements. Through our experiments, we highlight key practical factors contributing to the diminished channel reciprocity and demonstrate that Pearson's correlation and time-lagged cross-correlation can effectively measure and assess the channel reciprocity property between two communicating devices. Building upon the experiments' findings, we then introduce a technique that exploits the reciprocity of collected CSI data, as well as its temporal variations and time shifts to enhance device authentication resiliency through an effective detection of replay attacks.