Robust Keystroke Biometric Anomaly Detection

The Keystroke Biometrics Ongoing Competition (KBOC) presented an anomaly detection challenge with a public keystroke dataset containing a large number of subjects and real-world aspects. Over 300 subjects typed case-insensitive repetitions of their first and last name, and as a result, keystroke sequences could vary in length and order depending on the usage of modifier keys. To deal with this, a keystroke alignment preprocessing algorithm was developed to establish a semantic correspondence between keystrokes in mismatched sequences. The method is robust in the sense that query keystroke sequences need only approximately match a target sequence, and alignment is agnostic to the particular anomaly detector used. This paper describes the fifteen best-performing anomaly detection systems submitted to the KBOC, which ranged from auto-encoding neural networks to ensemble methods. Manhattan distance achieved the lowest equal error rate of 5.32%, while all fifteen systems performed better than any other submission. Performance gains are shown to be due in large part not to the particular anomaly detector, but to preprocessing and score normalization techniques.

[1]  Jugurta R. Montalvão Filho,et al.  Contributions to empirical analysis of keystroke dynamics in passwords , 2015, Pattern Recognit. Lett..

[2]  Jugurta R. Montalvão Filho,et al.  KBOC: Keystroke biometrics OnGoing competition , 2016, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[3]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  John V. Monaco,et al.  The partially observable hidden Markov model and its application to keystroke dynamics , 2016, Pattern Recognit..

[5]  Arun Ross,et al.  Score normalization in multimodal biometric systems , 2005, Pattern Recognit..

[6]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[7]  Yu Zhong,et al.  Keystroke Dynamics User Authentication Based on Gaussian Mixture Model and Deep Belief Nets , 2013 .

[8]  John V. Monaco,et al.  Spoofing key-press latencies with a generative keystroke dynamics model , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[9]  Julian Fiérrez,et al.  One-handed Keystroke Biometric Identification Competition , 2015, 2015 International Conference on Biometrics (ICB).

[10]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[11]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[12]  Julian Fiérrez,et al.  Keystroke dynamics recognition based on personal data: A comparative experimental evaluation implementing reproducible research , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[13]  John V. Monaco Time intervals as a Behavioral Biometric , 2015 .

[14]  Christophe Rosenberger,et al.  A review on the public benchmark databases for static keystroke dynamics , 2015, Comput. Secur..

[15]  Patrick Bours,et al.  Performance of keystroke dynamics when allowing typing corrections , 2014, 2nd International Workshop on Biometrics and Forensics.

[16]  T. Salthouse Effects of age and skill in typing. , 1984, Journal of experimental psychology. General.

[17]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[18]  Fred J. Damerau,et al.  A technique for computer detection and correction of spelling errors , 1964, CACM.

[19]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[20]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[21]  Yu Zhong,et al.  Recent Advances in User Authentication Using Keystroke Dynamics Biometrics , 2015 .

[22]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[23]  Roy A. Maxion,et al.  The Effect of Clock Resolution on Keystroke Dynamics , 2008, RAID.

[24]  John V. Monaco,et al.  The Partially Observable Hidden Markov Model with Application to Keystroke Biometrics , 2016, ArXiv.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[27]  Javier Garrido Salas,et al.  BiosecurID: a multimodal biometric database , 2009, Pattern Analysis and Applications.

[28]  Sung-Hyuk Cha,et al.  Recent Advances in the Development of a Long-Text-Input Keystroke Biometric Authentication System for Arbitrary Text Input , 2013, 2013 European Intelligence and Security Informatics Conference.

[29]  Pascal Vincent,et al.  Contractive Auto-Encoders: Explicit Invariance During Feature Extraction , 2011, ICML.

[30]  Julian Fiérrez,et al.  Score normalization for keystroke dynamics biometrics , 2015, 2015 International Carnahan Conference on Security Technology (ICCST).

[31]  Yu Zhong,et al.  Keystroke Dynamics User Authentication Using Advanced Machine Learning Methods , 2015 .

[32]  Sébastien Marcel,et al.  Keystroke Biometrics Ongoing Competition , 2016, IEEE Access.

[33]  Roy A. Maxion,et al.  Comparing anomaly-detection algorithms for keystroke dynamics , 2009, 2009 IEEE/IFIP International Conference on Dependable Systems & Networks.