Proceedings of International Conference on Applied Innovation in IT
2020/03/10, Volume 8, Issue 1, pp.77-86
Hidden Authentication of the User Based on Neural Network Analysis of the Dynamic Profile
Anastasiya Sivova, Alexey Vulfin, Konstantin Mironov, Anastasiya Kirillova
Abstract: The problem of continuous hidden user authentication based on the analysis of keyboard handwriting is considered. The main purpose of the analysis is to continuously verify the identity of the subject during his work on the keyboard. The aim of the work is to increase the efficiency of hidden user authentication algorithms based on a neural network analysis of a dynamic profile, formed by keyboard handwriting. The idea of user authentication using keyboard handwriting is based on measuring the time of keystrokes and the intervals between keystrokes, followed by comparing the resulting data set with the stored dynamic user profile. Studies have shown that analyzing the average value of the time each key is pressed is inefficient. It is proposed to analyze the holding time of a combination of several keys and the time between their presses. An approach in which not the times of pressing individual keys, but the parameters of pressing the most common letter combinations are analyzed, will increase the accuracy of recognition of dynamic images. An algorithm and software implementation for Russian keyboard layout have been developed, experiments conducted on field data allow us to conclude that the proposed method is effectively used to authenticate the user using keyboard handwriting.
Keywords: Keyboard Handwriting, Hidden Authentication, Neural Network Classifier
- M.N. Eshwarappa and M.V. Latte, “Multimodalbiometric person authentication using speech,signature and handwriting features,” InternationalJournal of Advanced Computer Science andApplications, Special Issue on Artificial Intelligence.2011, pp. 77-86.
- T.V. Zhashkova, O.M. Sharunova andE.Sh. Isyanova, “Neural network identification of aperson’s personality type by keyboard handwriting,”International Student Scientific Herald, 2015, no. 3.
- M. Cortopassi and E. Endejan, “Method andapparatus for using pressure information forimproved computer controlled handwritingrecognition, data entry and user authentication,” U.S.Patent, no. 6,707,942, 24 March 2004.
- S.M. Didenko, “Development and research of acomputer model for the dynamics of the user-mousesystem”, Tyumen, 2007.
- ГОСТ Р 54412-2011 – ISO/IEC/TR 24741:2007“Information technology. Biometrics. Biometricstutorial,” Standartinform, 2012.
- ГОСТ Р ISO/IEC 19794-2008 “Automaticidentification. Biometric identification. Formats forthe exchange of biometric data,” Standartinform,2009.
- ГОСТ Р ISO/IEC 1978-4-2014 “Informationtechnology. Biometrics. Biometric softwareinterface,” Standartinform, 2016.
- A.V. Skubitsky, “Analysis of the applicability of themethod of reconstructing dynamic systems inbiometric identification systems by keyboardhandwriting,” Informacionnye tehnologii, vol. 6,no. 1, 2008.
- R. Sharipov, M. Tumbinskaya and A. Abzalov,“Analysis of Users' Keyboard Handwriting based onGaussian Reference Signals,” 2019 InternationalRussian Automation Conference (RusAutoCon).IEEE, 2019, pp. 1-5.
- O. Vysotska and A. Davydenko, “Keystroke PatternAuthentication of Computer Systems Users as One ofthe Steps of Multifactor Authentication,”International Conference on Computer Science,Engineering and Education Applications. Springer,Cham, 2019, pp. 356-368.
- R. Chen, S. Kutten and E. Biham, “Userauthentication system and methods,” U.S. Patentno. 9,680,644, 13 June 2017.
- V.I. Vasiliev and B.G. Ilyasov, “Intelligentmanagement systems. Theory and practice,” tutorial.M: M.: Radiotehnika, 2009, 392 p.
- Z.H.U. Yunzhou, and X. Jiang, “System and methodfor user authentication with exposed and hiddenkeys,” U.S. Patent no. 8,132,020, 6 March 2012.
- A. Schwartz and G.A. Woodward, “Composition andmethod for hidden identification,” U.S. Patentno. 4,767,205, 30 August 1988.
- N. Harun, W.L. Woo and S.S. Dlay, “Performance ofkeystroke biometrics authentication system usingartificial neural network (ANN) and distanceclassifier method,” International Conference onComputer and Communication Engineering(ICCCE'10), IEEE, 2010, pp. 1-6.
- T. Thadewald and H. Büning, “Jarque–Bera test andits competitors for testing normality–a powercomparison,” Journal of Applied Statistics, vol. 34,no. 1, 2007, pp. 87-105.
- N.M. Razali and Y.B. Wah, “Power comparisons ofshapiro-wilk, kolmogorov-smirnov, lilliefors andanderson-darling tests,” Journal of statisticalmodeling and analytics, vol. 2, no. 1, 2011, pp. 21-33.