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 informationtechnology system. The goal here is to demonstrate thefeasibility of using Radio Frequency (RF) air monitoring toaugment 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/gWiFi and 4G 802.16 WiMAX. Proof-of-concept results arepresented to demonstrate the effectiveness of a “Learningfrom Signals” (LFS) classifier with Gaussian kernel band-width parameters optimally determined through DifferentialEvolution (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 isused for intra-manufacturer (like-modeldevices from a givenmanufacturer) discrimination of IEEE compliant 802.11aWiFi devices and 802.16e WiMAX devices. A comparativeperformance assessment is provided using results fromthe 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 SDfingerprint features for both classifiers. Finally, the impactof Gaussian, triangular, and uniform kernel functions onclassifier performance is demonstrated. Preliminary resultsof the DE-optimized classifier are very promising, with correct classification improvement of 15% to 40% realizedover the range of signal to noise ratios considered.

Index Terms—Wireless, Security, Fingerprinting, Differ¬ential Evolution, Genetic, Algorithm, 4G, 802.16, WiMAX,802.11, WiFi, Learning from Signals

Cite:Paul Harmer, Michael Temple, Mark Buckner, and Ethan Farquhar, "4G Security Using Physical Layer RF-DNA with DE-Optimized LFS Classification," Journal of Communications, vol. 6, no.9, pp.671-681, 2011. Doi: 10.4304/jcm.6.9.671-681