MLP neural network for keystroke-based user identification system

Author

Popovici, Eduard C. ; Guta, Ovidiu G. ; Stancu, Liviu A. ; Arseni, Stefan C. ; Fratu, Octavian

Author_Institution

ETTI Fac., “Politeh.” Univ. of Bucharest, Bucharest, Romania

Volume

01

fYear

2013

fDate

16-19 Oct. 2013

Firstpage

155

Lastpage

158

Abstract

In this paper we introduce a continuous authentication system based on keystroke dynamics (BIOMETRIC). We also propose two algorithms for extracting patterns and validating the user, both intended to be used in the same time to improve the overall performance of the validation process. The first one is based on a Multi Layer Perceptron (MLP) Neural Network and the second one relies on a trust algorithm that uses the Bhattacharyya coefficient.

Keywords

authorisation; keyboards; multilayer perceptrons; trusted computing; BIOMETRIC project; Bhattacharyya coefficient; MLP neural network; continuous authentication system; keystroke based user identification system; keystroke dynamics; multilayer perceptron neural network; pattern extraction; trust algorithm; user validation; Authentication; Data mining; Neural networks; Neurons; Standards; Training; Vectors; Bhattacharyya coefficient; Keystroke dynamics; MLP Neural Network; User identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Telecommunication in Modern Satellite, Cable and Broadcasting Services (TELSIKS), 2013 11th International Conference on

Conference_Location

Nis

Print_ISBN

978-1-4799-0899-8

Type

conf

DOI

10.1109/TELSKS.2013.6704912

Filename

6704912