Cyber-Physical Security with RF Fingerprint Classification through Distance Measure Extensions of Generalized Relevance Learning Vector Quantization

Abstract

Radio frequency (RF) fingerprinting extracts fingerprint features from RF signals to protect against masquerade attacks by enabling reliable authentication of communication devices at the “serial number” level. Facilitating the reliable authentication of communication devices are machine learning (ML) algorithms which find meaningful statistical differences between measured data. The Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier is one ML algorithm which has shown efficacy for RF fingerprinting device discrimination. GRLVQI extends the Learning Vector Quantization (LVQ) family of “winner take all” classifiers that develop prototype vectors (PVs) which represent data. In LVQ algorithms, distances are computed between exemplars and PVs, and PVs are iteratively moved to accurately represent the data. GRLVQI extends LVQ with a sigmoidal cost function, relevance learning, and PV update logic improvements. However, both LVQ and GRLVQI are limited due to a reliance on squared Euclidean distance measures and a seemingly complex algorithm structure if changes are made to the underlying distance measure. Herein, the authors (1) develop GRLVQI-D (distance), an extension of GRLVQI to consider alternative distance measures and (2) present the Cosine GRLVQI classifier using this framework. To evaluate this framework, the authors consider experimentally collected Z-wave RF signals and develop RF fingerprints to identify devices. Z-wave devices are low-cost, low-power communication technologies seen increasingly in critical infrastructure. Both classification and verification, claimed identity, and performance comparisons are made with the new Cosine GRLVQI algorithm. The results show more robust performance when using the Cosine GRLVQI algorithm when compared with four algorithms in the literature. Additionally, the methodology used to create Cosine GRLVQI is generalizable to alternative measures.

Applying Ateb–Gabor Filters to Biometric Imaging Problems

“…Biometric systems have good performance with good input quality. However, their performance deteriorates sharply when poor quality input enters the system [20]. Examples of bad data can be noisy scans with low resolution fingerprints.…”

Topological Data Analysis for Enhancing Embedded Analytics for Enterprise Cyber Log Analysis and Forensics

“…For the model in Figure 10a, a cosine metric was used along with kurtosis and variance lenses. Cosine distances can be useful because they are translation variant but scale invariant, in contrast to Euclidean distances [37].…”