Oleksiy Mazhelis
-
One-Class Classifiers: A Review and Analysis of Suitability in the Context of Mobile-Masquerader Detection
arima:1877 -
Revue Africaine de Recherche en Informatique et Mathématiques Appliquées,
September 30, 2007,
Volume 6, april 2007, joint Special Issue ARIMA/SACJ on Advances in end-user data mining techniques
-
https://doi.org/10.46298/arima.1877
One-Class Classifiers: A Review and Analysis of Suitability in the Context of Mobile-Masquerader Detection
Authors: Oleksiy Mazhelis 1
NULL
Oleksiy Mazhelis
1 Department of Computer Science and Information Systems
One-class classifiers employing for training only the data from one class are justified when the data from other classes is difficult to obtain. In particular, their use is justified in mobile-masquerader detection, where user characteristics are classified as belonging to the legitimate user class or to the impostor class, and where collecting the data originated from impostors is problematic. This paper systematically reviews various one-class classification methods, and analyses their suitability in the context of mobile-masquerader detection. For each classification method, its sensitivity to the errors in the training set, computational requirements, and other characteristics are considered. After that, for each category of features used in masquerader detection, suitable classifiers are identified.
Costante, Elisa; Den Hartog, Jerry; PetkoviÄ, Milan; Etalle, Sandro; Pechenizkiy, Mykola, 2014, Hunting The Unknown, Data And Applications Security And Privacy XXVIII, pp. 243-259, 10.1007/978-3-662-43936-4_16.