4G Security Using Physical Layer RF-DNA with DE-Optimized LFS Classification
Paul K. Harmer, Michael A. Temple, Mark A. Buckner, Ethan D. Farquhar · Journal of Communications · 2011
Abstract—Wireless communication networks remain un-der attack with ill-intentioned “hackers ” routinely gain-ing unauthorized access through Wireless Access Points (WAPs)–one of the most vulnerable points in an information technology system. The goal here is to demonstrate the feasibility of using Radio Frequency (RF) air monitoring to augment conventional bit-level security at WAPs. The spe-cific networks of interest are those based on Orthogonal Fre-quency Division Multiplexing (OFDM), to include 802.11a/g WiFi and 4G 802.16 WiMAX. Proof-of-concept results are presented to demonstrate the effectiveness of a “Learning from Signals ” (LFS) classifier with Gaussian kernel band-width parameters optimally determined through Differential Evolution (DE). The resultant DE-optimized LFS classifier is implemented within an RF “Distinct Native Attribute ” (RF-DNA) fingerprinting process using both Time Domain (TD) and Spectral Domain (SD) input features. The RF-DNA is used for intra-manufacturer (like-model devices from a given manufacturer) discrimination of IEEE compliant 802.11a WiFi devices and 802.16e WiMAX devices. A comparative performance assessment is provided using results from the proposed DE-optimized LFS classifier and a Bayesian-based Multiple Discriminant Analysis/Maximum Likelihood (MDA/ML) classifier as used in previous demonstrations. The assessment is performed using identical TD and SD fingerprint features for both classifiers. Finally, the impact of Gaussian, triangular, and uniform kernel functions on classifier performance is demonstrated. Preliminary results of the DE-optimized classifier are very promising, with correct classification improvement of 15 % to 40 % realized over the range of signal to noise ratios considered.