Anomaly detection through keystroke and tap dynamics implemented via machine learning algorithms
Anomaly detection through keystroke and tap dynamics implemented via machine learning algorithms
In our world of growing machine intelligence and increasing security risks, there is a dire need for authentication to be liberated from password dependency and restrictions. This paper discusses the implementation of keystrokebiometrics to enhance security using machine-learning algorithms on both Windows and Android. Our research analyzesa user’s behavior for authorization purposes by capturing the user’s typing pattern. The system extracts several featuresfrom the user’s typing pattern to apply unary classification for user behavior analysis so that we can detect unauthorizedusers. Our system implements machine learning on tap dynamics in Android, allowing both training and prediction andovercoming its computational restrictions.
___
- [1] Forsen G, Nelson M, Staron R, Personal Attributes Authentication Techniques. Technical Report RADC-TR 77-333. Rome, NY, USA: Rome Air Development Center, 1977.
- [2] The PS, Teoh ABJ, Yue S. A survey of keystroke dynamics biometrics. Sci World J 2013; 24: 408280.
- [3] Killourhy KS, Maxion RA. Comparing anomaly-detection algorithms for keystroke dynamics. In: IEEE/IFIP 2009 International Conference on Dependable Systems & Networks; 29 June–2 July 2009; Lisbon, Portugal. New York, NY, USA: IEEE. pp. 125-134.
- [4] Douhou S, Magnus JR. The reliability of user authentication through keystroke dynamics. Stat Neerl 2009; 63:432- 449.
- [5] Crawford H. Keystroke dynamics: characteristics and opportunities. In: 2010 Eighth International Conference on Privacy, Security and Trust; 17–19 August 2010; Ottawa, Canada. New York, NY, USA: IEEE. pp. 205-212.
- [6] Maxion RA, Killourhy KS. Keystroke biometrics with number-pad input. In: IEEE/IFIP 2010 International Conference on Dependable Systems & Networks; 28 June–1 July 2010; Chicago, IL, USA. New York, NY, USA: IEEE. pp. 201-210.
- [7] Rundhaug FEN. Keystroke dynamics-Can attackers learn someone’s typing characteristics? MSc, Gjøvik University College, Gjøvik, Norway, 2007.
- [8] Antal M, Szabó LZ, László I. Keystroke dynamics on Android platform. In: 8th International Conference of Interdisciplinarity in Engineering, INTER-ENG; 9–10 October 2014; Tirgu-Mures, Romania. Amsterdam, the Netherlands: Elsevier. pp. 820-826.
- [9] Alghamdi SJ, Elrefaei LA. Dynamic user verification using touch keystroke based on medians vector proximity. In: IEEE 7th International Conference on Computational Intelligence, Communication Systems and Networks; 3–5 June 2015; Riga, Latvia. New York, NY, USA: IEEE. pp. 121-126.
- [10] Sun L, Wang Y, Cao B, Yu PS, Srisa-an W, Leow AD. Sequential keystroke behavioral biometrics for mobile user identification via multi-view deep learning. In: European Conference on Machine Learning and Knowledge Discovery in Databases; 18–22 September 2017; Skopje, Macedonia. pp. 228-240.
- [11] Sahs J, Khan L. A machine learning approach to Android malware detection. In: 2012 European Intelligence and Security Informatics Conference; 22–24 August 2012; Odense, Denmark. New York, NY, USA: IEEE. pp. 141-147.
- [12] Grant H. TapDynamics: Strengthening User Authentication on Mobile Phones with Keystroke Dynamics. Technical Report. Stanford, CA, USA: Stanford University, 2014.
- [13] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al. Scikit-learn: Machine learning in Python. J Mach Learn Res 2011; 12: 2825-2830.
- [14] Schölkopf B, Platt JC, Shawe-Taylor JC, Smola AJ, Williamson RC. Estimating the support of a high-dimensional distribution. Neural Comput 2001; 13: 1443-1471.