Article

Article title IDENTIFICATION OF USER BASED ON WORK DYNAMICS WITH “MOUSE” POINTING DEVICE USING THE NEURAL NETWORKS
Authors D.P. Rublev, V.M. Fedorov
Section SECTION II. APPLIED INFORMATION SECURITY
Month, Year 05, 2017 @en
Index UDC 004.056:061.68
DOI
Abstract In this paper identification problem for interacting with “mouse” pointing device by vibroacoustic signal originated from user is reviewed. Capabilities of data collection for user identification on vibroacoustic channel and advantages of this technique are shown. Operator’s workplace modifications, stand description and software are considered. Features of vibroacoustic signals obtained from user’s interaction with mouse are reviewed, stable features which allow mouse movement detection have been selected from Fourier transform, cepstral and linear prediction coefficients. Feature vectors have been formed by the relative in one-sample shift intervals of user activity which are global time-invariants. Sync scheme for keylogger’s log file and vibroacoustics signal for precise localization of keypress moments with mouse movement detection and feature vectors creation is reviewed, precise localization of mouse movements time moments for correct feature vectors forming have been done. Two and seven users identification results based on ANN learned with dichotomy scheme. The dependencies of neural network simulation errors on hidden layers dimensions, activation functions and input classes number have been considered, with correct identification probability verified increase dependent on informational signal length, according estimations of necessary length for identification rate comparable with typing techniques have been obtained. User identification is done on a basis of feature vectors formed by sliding windows, vibroacoustics of mouse movement noises is shown, dependencies of neural network errors on hidden layers neurons quantity, activation functions and output classes are considered.

Download PDF

Keywords Vibroacoustic signal; discrete Fourier transform; cepstral coefficients, neural networks, linear prediction coefficients, identification.
References 1. Rublev D.P. Fedorov V.M., Makarevich O.B. Digital Camera Identification System, Aksaray, Turkey SIN '13, pp. 297-300.
2. Ilonen J. Keystroke Dynamics, Lappeenranta University of Technology, 2008, pp. 108-111.
3. Fedorov, V.M., Rublev D.P., Panchenko E.M. Segmentatsiya vibroakusticheskikh signalov, voznikayushchikh pri nazhatii/otpuskanii klavish klaviatury [Segmentation of vibro-acoustic signals generated when you press/release key], Materialy dokladov konferentsii «Informatsionnaya bezopasnost' 2013» [Materials of the conference "Information security 2013"], 2013, pp. 130-136.
4. Fedorov V.M., Rublev D.P. Metody predvaritel'noy obrabotki vibroakusticheskikh signalov ot klaviatury voznikayushchikh pri nabore teksta [Methods pre-processing vibro-acoustic signals from the keyboard occurs when typing], Informatsionnoe protivodeystvie ugrozam terrorizma [Information Counteraction to Terrorism Threats], 2012, No. 18, pp. 172-175.
5. Fedorov V.M., Rublev D.P. Fil'tratsiya vibroakusticheskikh signalov ot klaviatury i manipulyatora mysh', voznikayushchikh pri rabote operatora [Filtering acoustic signals from the keyboard and mouse that occurs when the operator], Informatsionnoe protivodeystvie ugrozam terrorizma [Information Counteraction to Terrorism Threats], 2012, No. 19, pp. 160-162.
6. Babenko L.K., Fedorov V.M., Yurkov P.Yu. Autentifikatsiya diktora s ispol'zovaniem izmenyaemogo mnozhestva klyuchevykh slov [Speaker authentication using a mutable set of key words], Izvestiya TRTU [Izvestiya TSURE], 2004, No. 1 (36), pp. 289-295.
7. Fedorov V.M., Rublev D.P. Obrabotka vibroakusticheskikh shumov, voznikayushchikh pri rabote pol'zovatelya s klaviaturoy [Processing of vibroacoustic noise originated from user work with keyboard], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2012, No. 12, pp. 75-78.
8. Fedorov V.M., Rublev D.P. Identifikatsiya pol'zovatelya po vibroakusticheskim shumam, voznikayushchim pri nabore parol'noy frazy na klaviature [User identification for vibro-acoustic noise that occurs when typing in a passphrase on the keyboard], Sbornik trudov konferentsii «Sistemotekhnika» [Proceedings of the conference "systems Engineering"], 2013, pp. 158-163.
9. Fedorov V.M., Rublev D.P. Identifikatsiya nabiraemogo na klaviature teksta po vibroakusticheskim shumam [Identification of text typed on keyboard by vibroacoustics noises], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2014,
No. 2 (151), pp. 67-73.
10. Bergadano F., Gunetti D., and Picardi C. User authentication through keystroke dynamics, ACM Transactions on Information and System Security, 2002, No. 5, pp. 367-397.
11. Salima Douhou Jan R. Magnus The reliability of user authentication through keystroke dy-namics, Statistica Neerlandica, 2009, Vol. 63, No. 4, pp. 432-449.
12. Hu J., Gingrich D. A k-Nearest Neighbor Approach for User Authentication through Biometric Keystroke Dynamics, ICC '08. IEEE International Conference on Communications, 2008, pp. 1556-1560.
13. Rezaei A. and Mirzakochaki S. A Novel Approach for Keyboard Dynamics Authentication based on Fusion of Stochastic Classifiers, IJCSNS International Journal of Computer Science and Network Security, 2012, Vol. 12, No. 8, pp. 60-68.
14. Shanmugapriya D., Padmavathi G. A Survey of Biometric keystroke Dynamics: Approaches, Security and Challenges, (IJCSIS) International Journal of Computer Science and Information Security, 2009, Vol. 5, No. 1, pp. 1-8.
15. Yu Zhong, Yunbin Deng, Anil K. Jain. Keystroke Dynamics for User Authentication, EEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2012, pp. 117-123.
16. Sheng Y, Phoha V, Rovnyak S. A parallel decision tree-based method for user authentication based on keystroke patterns, IEEE Trans Syst Man Cybern B Cybern, 2005, No. 35, pp. 826-833.
17. Bleha S., Slivinsky C., Hussein B. Computer-access security systems using keystroke dynamics, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, No. 12, pp. 1217-1222.
18. Shrijit S., Joshi V. Investigating Hidden Markov Models capabilities in Anomaly Detection, ACM-SE 43 Proceedings of the 43rd annual Southeast regional conference, 2005, Vol. 1,
pp. 98-103.
19. Vinar T. Enhancements to Hidden Markov Models for Gene Finding and Other Biological Applications, Computer Science, University of Waterloo, Waterloo, Ontario, Canada, 2005, pp. 162-164.
20. Mansfield A.J., Wayman J.L. Best Practices in Testing and Reporting Performance of Biometric Devices, Center for Mathematics and Scientific Computing, National Physics Laboratory, 2002, pp. 13-25.

Comments are closed.