Marco Aurélio da Silva Cruz
ABSTRACT
Several studies have investigated how to use Machine Learning algorithms to recognize users based on keystroke dynamic. All those studies required Feature Engineering (FE), i.e., a process in which specialists choose what attributes should be considered for learning. However, this process is susceptible to problems such as original information loss or inappropriate attribute choices. Thus, the objective of this work is to demonstrate the hypothesis that user recognition algorithms applied to keystroke dynamics raw (original) data can perform better than the ones that depend on FE. Therefore, this work proposes a deep neural network named DRK. The proposed network contains layers that learn adequate data representations to perform user recognition based on keystroke dynamics raw data, avoiding FE. Experiments compared DRK with four other deep neural networks that use FE in four datasets with 280 users. The proposed network achieved better results in all datasets, showing strong evidence that the stated hypothesis is, in fact, valid.
- M. Ali, J. Monaco, C. Tappert, and M. Qiu. 2017. Keystroke Biometric Systems for User Authentication. Journal of Signal Processing Systems 86, 2 (mar 2017), 175--190. Google Scholar
Digital Library
- M. Antal and L. Nemes. 2016. The MOBIKEY keystroke dynamics password database: Benchmark results. In Advances in Intelligent Systems and Computing, Vol. 465. Springer, 35--46.Google Scholar
- M. Antal, L. Z. Szabó, and I. László. 2015. Keystroke dynamics on android platform. Procedia Technology 19 (2015), 820--826.Google ScholarCross Ref
- L. C. F. Araújo, L. H. R. Sucupira, M. G. Lizarraga, L. L. Ling, and J. B. T. Yabu-Uti. 2005. User authentication through typing biometrics features. IEEE transactions on signal processing 53, 2 (2005), 851--855. Google ScholarDigital Library
- S. P. Banerjee and D. L. Woodard. 2012. Biometric authentication and identification using keystroke dynamics: A survey. Journal of Pattern Recognition Research 7, 1 (2012), 116--139.Google ScholarCross Ref
- R. Baskerville, F. Rowe, and F.-C. Wolff. 2012. Functionality vs. Security in IS: Tradeoff or equilibrium. In International Conference on Information Systems, ICIS 2012, Vol. 2. Association for Information Systems, 1210--1229.Google Scholar
- Y. Bengio, A. Courville, and P. Vincent. 2013. Representation learning: A review and new perspectives. IEEE Trans. Pattern Anal. and Mach. Intell. 35, 8 (2013), 1798--1828. Google ScholarDigital Library
- H. Çeker and S. Upadhyaya. 2017. Sensitivity analysis in keystroke dynamics using convolutional neural networks. In 2017 IEEE Workshop on Information Forensics and Security (WIFS). 1--6.Google Scholar
- M. Cruz, J. Duarte, and R. Goldschmidt. 2017. Dinâmica da Digitação Aplicada à Autenticação Periódica de Usuários em Ambientes Virtuais de Aprendizagem. Revista Brasileira de Informática na Educação 2 (2017), 1--30.Google Scholar
- M. A. S. Cruz and R. R. Goldschmidt. 2018. Algoritmos de Aprendizado de Máquina Aplicados ao Reconhecimento de Usuário Baseado na Dinâmica da Digitação: Um Estudo Comparativo. SBSeg 2 (2018), 1--30.Google Scholar
- Y. Deng and Y. Zhong. 2013. Keystroke dynamics user authentication based on gaussian mixture model and deep belief nets. ISRN Signal Processing (2013), 1--30.Google Scholar
- M. El-Abed, M. Dafer, and R. E. Khayat. 2014. RHU Keystroke: A mobile-based benchmark for keystroke dynamics systems. In 2014 Int. Carnahan Conf. on Security Technology (ICCST). 1--4.Google Scholar
- K. Faceli, A. C. Lorena, J. Gama, and A. Carvalho. 2011. Inteligência Artificial: Uma abordagem de aprendizado de máquina. Vol. 2. LTC.Google Scholar
- F. Ghahramani and J. Wang. 2017. Adoption of an Authentication System: Is Security the Only Consideration?. In International Conference on Information Systems - ICIS. 1--20.Google Scholar
- R. Giot and et al. 2009. GREYC Keystroke: a Benchmark for Keystroke Dynamics Biometric Systems. IEEE Int. Conf. on Biometrics: Theory, Applications and Systems (BTAS 2009) (2009). Google ScholarDigital Library
- I. Goodfellow, Y. Bengio, and A. Courville. 2016. Deep Learning. MIT Press. Google ScholarDigital Library
- K. He, X. Zhang, S. Ren, and J. Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proc. of the IEEE Int. Conf. on computer vision. 1026--1034. Google ScholarDigital Library
- G. E. Hinton, S. Osindero, and Y.-W. Teh. 2006. A fast learning algorithm for deep belief nets. Neural computation 18, 7 (2006), 1527--1554. Google ScholarDigital Library
- S. Hochreiter and J. Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (1997), 1735--1780. arXiv:1206.2944 Google ScholarDigital Library
- K. S. Killourhy and R. A. Maxion. 2009. Comparing anomaly-detection algorithms for keystroke dynamics. In Dependable Systems & Networks, 2009. DSN'09. IEEE/IFIP Int. Conf. on. 125--134.Google Scholar
- P. Kobojek and K. Saeed. 2016. Application of Recurrent Neural Networks for User Verification based on Keystroke Dynamics. Journal of Telecommunications and Information Technology 1, 3 (2016), 80.Google Scholar
- Y. Lecun, Y. Bengio, and G. Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444. arXiv:arXiv:1312.6184v5Google Scholar
- A. L. Maas, A. Y. Hannun, and A. Y. Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In Proc. icml, Vol. 30. 3.Google Scholar
- G. A. Mack and J. H. Skillings. 1980. A Friedman-Type Rank Test for Main Effects in a Two-Factor ANOVA. J. Amer. Statist. Assoc. 75, 372 (1980), 947--951.Google ScholarCross Ref
- S. Maheshwary, S. Ganguly, and V. Pudi. 2017. Deep secure: A fast and simple neural network based approach for user authentication and identification via keystroke dynamics. In IWAISe: First Int. Workshop on Artificial Intelligence in Security. 59.Google Scholar
- F. Monrose and A. D. Rubin. 2000. Keystroke dynamics as a biometric for authentication. Future Generation Computer Systems 16, 4 (2000), 351--359. Google ScholarDigital Library
- P. H. Pisani and A. C. Lorena. 2013. A systematic review on keystroke dynamics. Journal of the Brazilian Computer Society 19, 4 (nov 2013), 573--587.Google ScholarCross Ref
- E. Prado and C. A. de Souza. 2014. Fundamentos de sistemas de informação. Vol. 1. Elsevier Brasil.Google Scholar
- F. Rosenblatt. 1962. Principles of Neurodynamics. Spartan Book, New York.Google Scholar
- S. Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016).Google Scholar
- M. Sêmola. 2014. Gestão da segurança da informação. Vol. 2. Elsevier Brasil.Google Scholar
- N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 1929--1958. Google ScholarDigital Library
- P. S. Teh, A. B. J. Teoh, and S. Yue. 2013. A survey of keystroke dynamics biometrics. The Scientific World Journal 2013 (2013), 1--30.Google ScholarCross Ref
Index Terms
- Deep Neural Networks Applied to User Recognition Based on Keystroke Dynamics: Learning from Raw Data
Recommendations
Keystroke dynamics-based user authentication service for cloud computing
User authentication is a crucial requirement for cloud service providers to prove that the outsourced data and services are safe from imposters. Keystroke dynamics is a promising behavioral biometrics for strengthening user authentication, however, ...
User authentication method based on keystroke dynamics and mouse dynamics using HDA
AbstractBiometric authentication has advantages over traditional authentication based on passwords or pin number (PIN) in that it is based on the user's inherent characteristics which is not easily stolen or lost. Keystroke dynamics and mouse dynamics are ...
Continuous authentication by free-text keystroke based on CNN plus RNN
AbstractPersonal keystroke mode is difficult to imitate and can therefore be used for identity authentication. According to the keystroke data when a person inputs free text, the keystroke habit of the person can be learned. Detecting a user’s keystroke ...
Comments