Using Support Vector Machines for Passive Steady State RF Fingerprinting

Zamora, Georgina O'Mahony; Bergin, Susan; Kennedy, Irwin O.

doi:10.1007/978-90-481-3662-9_31

Cited by 14 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first RF fingerprinting system was utilized in the Vietnam War to differentiate between a friendly and foe radar [10]. In the past few years, researchers explored many RF fingerprinting techniques for identification of transmitters in commercial spheres [13,[21][22][23][24]. One such example is in cellular industry, where RF fingerprinting is used to prevent cell phone cloning [25,26].…”

Section: Rf Fingerprinting Backgroundmentioning

confidence: 99%

Analysis of impersonation attacks on systems using RF fingerprinting and low-end receivers

Rehman

Sowerby

Coghill

2014

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Section: Rf Fingerprinting Backgroundmentioning

confidence: 99%

Analysis of impersonation attacks on systems using RF fingerprinting and low-end receivers

Rehman

Sowerby

Coghill

2014

Journal of Computer and System Sciences

View full text Add to dashboard Cite

“…Previous work on RF fingerprinting has focussed mainly on identifying different mobile phone handsets by manufacturer and by model [2,3]. While this work is relevant, the approach used is not sufficient for the five in the house problem.…”

Section: Problem Definitionmentioning

confidence: 99%

“…It has already been shown that standard RBF kernel SVMs have a high accuracy distinguishing between different transmitters [2]. Using this knowledge coupled with the PD estimates allows us to use these classifiers on the five in the house problem.…”

Section: Svm Classifier Implementationsmentioning

confidence: 99%

“…When the classifier is tested it is shown both positive samples and negative samples. It has also been shown that handsets of the same model can be harder to distinguish than handsets of a different model [2,3]. The Tiered, Weighted and Double classifiers are constructed in such a way as to potentially allow one of the sub-classifiers to avoid having multiple identical handsets, or if unavoidable at least favor one over the other.…”

Section: Svm Classifier Implementationsmentioning

confidence: 99%

“…The 3GPP UMTS standard recommends the uniquely identifying IMSI (International Mobile Subscriber Identifier) should not be sent in plain text over the air. We discuss this and other motivating aspects of the problem in more depth in papers published previously by the authors [2,3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Steady State RF Fingerprinting for Identity Verification: One Class Classifier versus Customized Ensemble

Kroon¹,

Bergin²,

Kennedy³

et al. 2010

Artificial Intelligence and Cognitive Science

Self Cite

View full text Add to dashboard Cite

Abstract.Mobile phone proliferation and increasing broadband penetration presents the possibility of placing small cellular base stations within homes to act as local access points. This can potentially lead to a very large increase in authentication requests hitting the centralized authentication infrastructure unless access is mediated at a lower protocol level. A study was carried out to examine the effectiveness of using Support Vector Machines to accurately identify if a mobile phone should be allowed access to a local cellular base station using differences imbued upon the signal as it passes through the analogue stages of its radio transmitter. Whilst allowing prohibited transmitters to gain access at the local level is undesirable and costly, denying service to a permitted transmitter is simply unacceptable. Two different learning approaches were employed, the first using One Class Classifiers (OCCs) and the second using customized ensemble classifiers. OCCs were found to perform poorly, with a true positive (TP) rate of only 50% (where TP refers to correctly identifying a permitted transmitter) and a true negative (TN) rate of 98% (where TN refers to correctly identifying a prohibited transmitter). The customized ensemble classifier approach was found to considerably outperform the OCCs with a 97% TP rate and an 80% TN rate.

show abstract