IEEE Transactions on Industrial Informatics · 2023 · 16 citations · 22 references
ComputingComputer EngineeringCybersecurityAuthenticationMobile ComputingMobile SecurityBiometric AuthenticationDevice AuthenticationDigital Image ProcessingMobile Device SecurityPhysical Layer SecurityWireless Channel ModelingMobile AuthenticationPhysical Layer AuthenticationSecure Authentication
Channel-state information (CSI)-based physical-layer authentication (PLA) has gained significant attention. However, in industrial mobile scenarios, the time-varying channels and changing device locations limit the reliability of CSI-based PLA algorithms. Furthermore, the performance of existing PLA algorithms degrades sharply at uncalibrated locations. To improve the reliability and robustness of authentication, we propose a new spatiotemporal gradient-based-PLA (STG-PLA) algorithm enhanced by CSI-to-image transformation. We first extract correlation and scattering features to depict the multidimensional channel properties, including selectivity and dispersion. We then convert several individual CSI sequences to a CSI-image. Therefore, the spatiotemporal correlation gradient of the CSI-sequences is reflected in one CSI-image. Both simulations and experiments show that STG-PLA reduces the authentication error rate from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$>10{\%}$</tex-math></inline-formula> (in existing studies) to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$< 1{\%}$</tex-math></inline-formula> , which signifies considerable progress toward the practical applicability. Furthermore, with no model retraining, STG-PLA exhibits the robust performance when the device moves to uncalibrated locations.
22
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text