This study investigates the feasibility of identifying age group, gender, handedness and number of hand(s) used of a user by measuring the typing pattern on a computer keyboard which has good impact on keystroke dynamics biometric user authentication system. Fuzzy-Rough Nearest Neighbour (FRNN) with the help of Vaguely Quantified Rough Set (VQRS) machine learning method was used to develop the model based on the collected typing pattern and evaluated the effectiveness of the classifier in this domain. Multiple benchmark datasets have been used to validate the proposed model in order to check the robustness of the proposed approach. The obtained results indicate that age group, gender, handedness, and a number of hand(s) used can be predicted by the way user type on a computer keyboard for a single predefined text. It is also observed that incorporation of such soft biometric traits as extra features with primary keystroke dynamics characteristics can be used to enhance the performance of keystroke dynamics systems pretending to be used in future at low cost. The model is developed with a limited number of samples collected from a small group of participants in a controlled environment. However, this model will be further trained and evaluated by some extra features which are easily available in each smartphone such as gyroscope and acceleration information. Identifying such traits are important issues in digital forensics, age-based access control, targeted advertisement and auto profiling of the users. It adopts a suitable method to be used on the desktop computer as well as a smartphone.

Keystroke Dynamics (KD), Soft Biometric, Fuzzy Rough NN (FRNN), Vaguely Quantified Rough Set (VQRS)Introduction

[1] D. Bartmann, I. Bakdi, and M. Achatz, “On the Design of an Authentication System Based on Keystroke Dynamics Using a Predefined Input Text,” Int. J. Inf. Secur. Priv., vol. 1, no. 2, pp. 1–12, 2007.
[2] P. H. Pisani, R. Giot, A. C. P. L. F. De Carvalho, and A. C. Lorena, “Enhanced template update: Application to keystroke dynamics,” Comput. Secur., vol. 60, pp. 134–153, 2016.
[3] P. S. Teh, S. Yue, and A. B. Teoh, “Feature Fusion Approach on Keystroke Dynamics Efficiency Enhancement,” Int. J. Cyber-Security Digit. Forensics, vol. 1, no. 1, pp. 20–31, 2012.
[4] R. Giot and C. Rosenberger, “A new soft biometric approach for keystroke dynamics based on gender recognition,” Int. J. Inf. Technol. Manag. Spec. Issue Adv. Trends Biometrics, vol. 11, no. August, pp. 1–16, 2012.
[5] A. K. Jain, S. C. Dass, and K. Nandakumar, “Can soft biometric traits assist user recognition ?,” pp. 1–12.
[6] A. Dantcheva, C. Velardo, A. D’Angelo, and J.-L. Dugelay, “Bag of soft biometrics for person identification: New trends and challenges,” Multimed. Tools Appl., vol. 51, no. 2, pp. 739–777, 2011.
[7] A. K. Jain, K. Nandakumar, X. Lu, and U. Park, “Integrating Faces , Fingerprints , and Soft Biometric Traits for User Recognition,” no. May, pp. 259–269, 2004.
[8] S. Z. S. Idrus, E. Cherrier, C. Rosenberger, and P. Bours, “Soft Biometrics For Keystroke Dynamics,” in 10th International Conference on Image Analysis and Recognition (ICIAR), 2013, pp. 11–18.
[9] Y. Uzun, K. Bicakci, and Y. Uzunay, “Could We Distinguish Child Users from Adults Using Keystroke Dynamics?,” 2014.
[10] C. Epp, M. Lippold, and R. L. Mandryk, “Identifying Emotional States Using Keystroke Dynamics,” Proc. SIGCHI Conf. Hum. Factors Comput. Syst., pp. 715–724, 2011.
[11] P. R. Letters et al., “Soft biometrics — combining body weight and fat measurements with fingerprint biometrics,” no. May 2016, 2006.
[12] A. K. Jain and U. Park, “Facial marks: Soft biometric for face recognition,” Proc. - Int. Conf. Image Process. ICIP, pp. 37–40, 2009.
[13] Z. Li, X. Zhou, and T. S. Huang, “Spatial Gaussian mixture model for gender recognition,” in IEEE 16th International Conference on Image Processing (ICIP 2009), 2009.
[14] S. Roy, U. Roy, and D. D. Sinha, “ACO-Random Forest Approach to Protect the Kids from Internet Threats through Keystroke,” Int. J. Eng. Technol., vol. (Accepted), pp. 2–9, 2017.
[15] J. L. Wayman, “Large-scale Civilian Biometric Systems-Issues and Feasibility,” in Proceedings of Card Tech/Secur Tech ID, 1997.
[16] S. Gutta, J. R. J. Huang, P. Jonathon, and H. Wechsler, “Mixture of experts for classification of gender, ethnic origin, and pose of human faces,” IEEE Trans. Neural Networks, vol. 11, no. 4, pp. 948–960, 2000.
[17] A. K. Jain, S. C. Dass, and K. Nandakumar, “Soft Biometric Traits for Personal Recognition Systems,” Proc. Int. Conf. Biometric Authentication, no. July, pp. 731–738, 2004.
[18] X. Lu and A. Jain, “Ethnicity identification from face images,” Proc. SPIE Conf. Biometric Technol. Hum. Identification, vol. 5404, pp. 114–123, 2004.
[19] H. Ailisto, E. Vildjiounaite, M. Lindholm, S. M. Mäkelä, and J. Peltola, “Soft biometrics-combining body weight and fat measurements with fingerprint biometrics,” Pattern Recognit. Lett., vol. 27, no. 5, pp. 325–334, 2006.
[20] U. Park and A. Jain, “Face matching and retrival using soft biometrics Information Forensics and Security,” IEEE Trans., vol. 5, no. 3, pp. 406–415, 2010.
[21] S. Roy, U. Roy, and D. D. Sinha, Efficacy of Typing Pattern Analysis in Identifying Soft Biometric Information and Its Impact in User Recognition, vol. 10590 LNCS. 2017.
[22] S. Roy, U. Roy, and D. D. Sinha, “Comparative study of various features-mining-based classifiers in different keystroke dynamics datasets,” in Smart Innovation, Systems and Technologies, vol. 50, 2016.
[23] K. S. Killourhy and R. A. Maxion, “Comparing anomaly-detection algorithms for keystroke dynamics,” in Proceedings of the International Conference on Dependable Systems and Networks, 2009, pp. 125–134.
[24] C. C. Loy, C. P. Lim, and W. K. Lai, “Pressure-based typing biometrics user authentication using the fuzzy ARTMAP neural network,” in International Conference on Neural Information Processing (ICONIP), 2005.
[25] L. Bello and M. Bertacchini, “Collection and publication of a fixed text keystroke dynamics dataset,” CACIC 2010 - XVI Congr. ARGENTINO CIENCIAS LA Comput., pp. 822–831, 2010.
[26] R. Giot, M. El-Abed, and C. Rosenberger, “Web-Based Benchmark for Keystroke Dynamics Biometric Systems: A Statistical Analysis,” Intell. Inf. hiding andmultimedia signal Process., pp. 11–15, 2012.
[27] J. Roth, X. Liu, A. Ross, and D. Metaxas, “Biometric Authentication via Keystroke Sound,” 2013 Int. Conf. biometrics, pp. 1–8, 2013.
[28] S. Z. S. Idrus, E. Cherrier, C. Rosenberger, and P. Bours, “Soft biometrics database: A benchmark for keystroke dynamics biometric systems,” in Biometrics Special Interest Group (BIOSIG), 2013 International Conference of the, 2013, no. September, pp. 1–8.
[29] M. El-Abed, M. Dafer, and R. El Khayat, “RHU Keystroke: A mobile-based benchmark for keystroke dynamics systems,” 2014 Int. Carnahan Conf. Secur. Technol., pp. 1–4, 2014.
[30] M. Antal and L. Z. Szabo, “An evaluation of one-class and two-class classification algorithms for keystroke dynamics authentication on mobile devices,” Proc. - 2015 20th Int. Conf. Control Syst. Comput. Sci. CSCS 2015, pp. 343–350, 2015.
[31] J. Montalvão, E. O. Freire, M. A. Bezerra, and R. Garcia, “Contributions to empirical analysis of keystroke dynamics in passwords,” Pattern Recognit. Lett., 2015.
[32] K. S. Killourhy, “A Scientific Understanding of Keystroke Dynamics,” Dr. Thesis, Sch. Comput. Sci. Comput. Sci. Dep. CarnegieMellon Univ. Pittsburgh, PA 15213, no. January, pp. 1–198, 2012.
[33] S. Z. S. Idrus, E. Cherrier, C. Rosenberger, and P. Bours, “Soft biometrics database: A benchmark for keystroke dynamics biometric systems,” Biometrics Spec. Interes. Gr. (BIOSIG), 2013 Int. Conf., no. September, pp. 1–8, 2013.
[34] R. Jensen and C. Cornelis, “Fuzzy Rough Nearest Neighbour Classification and Prediction,” Theor. Comput. Sci., vol. 412(42), pp. 5871–5884, 2011.
[35] M. Sarkar, “Fuzzy-rough nearest neighbor algorithms in classification,” Fuzzy Sets Syst., vol. 158, no. 19, pp. 2134–2152, 2007.
[36] C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A Practical Guide to Support Vector Classification,” BJU Int., vol. 101, no. 1, pp. 1396–400, 2008.
[37] S. J. Alghamdi and L. A. Elrefaei, “Dynamic User Verification Using Touch Keystroke Based on Medians Vector Proximity,” Proc. - 7th Int. Conf. Comput. Intell. Commun. Syst. Networks, CICSyN 2015, pp. 121–126, 2015.
[38] S. Zulkarnain et al., “Keystroke Dynamics Performance Enhancement With Soft Biometrics.”
[39] S. Roy, U. Roy, and D. D. Sinha, “Comparative Study of Various Features-Mining-Based Classifiers in Different Keystroke Dynamics Datasets,” in Proceedings of First International Conference on Information and Communication Technology for Intelligent Systems, 2016, vol. 2, pp. 155–164.