User Keystroke Authentication Based on Convolutional Neural Network

  • Mengxin Liu
  • Jianfeng GuanEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 971)


Biometric authentication technology has become an important measure to protect user information security. Among them, keystroke authentication technology has attracted the attention of many researchers because of its low cost and high benefit. In recent years, various methods such as statistical methods and integrated models have been increasingly used in user keystroke authentication and have achieved relatively good results. However, few people try to convert keystroke data into images and tap spatial information between keystroke data. In this paper, we used a new way to convert keystroke data into images, then we use a binary model based on a Convolutional Neural Network (CNN) for each genuine user and try to import the transformed images into the CNN model. In this way, we can dig out the “spatial information” of keystroke features, which is the advantage over other models, and this method is first proposed for keystroke behavior authentication. In addition, we have also tried data augmentation, relu activation functions and dropout methods to reduce overfitting. In the end, we got an accuracy of 96.8%, which is about 10% higher than the previous work.


Keystroke authentication Convolutional neural network Information security Overfitting 


  1. 1.
    Azevedo, G.L.F.B.G., Cavalcanti, G.D.C., Filho, E.C.B.C.: Hybrid solution for the feature selection in personal identification problems through keystroke dynamics. In: International Joint Conference on Neural Networks, pp. 1947–1952 (2007). ISSN 2161-4393
  2. 2.
    Brown, M., Rogers, S.J.: User identification via keystroke characteristics of typed names using neural networks. Int. J. Man Mach. Stud. 39(6), 999–1014 (1993). Scholar
  3. 3.
    Casey, W., Morales, J.A., Mishra, B.: Threats from inside: dynamic utility (mis)alignments in an agent based model. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 7(1), 97–117 (2016). Scholar
  4. 4.
    Çeker, H., Upadhyaya, S.: Sensitivity analysis in keystroke dynamics using convolutional neural networks. In: IEEE Workshop on Information Forensics and Security (WIFS), pp. 1–6, December 2017.
  5. 5.
    Chen, C., Anada, H., Kawamoto, J., Sakurai, K.: A hybrid encryption scheme with key-cloning protection: user/terminal double authentication via attributes and fingerprints. J. Internet Serv. Inf. Secur. (JISIS) 6(2), 23–36 (2016). Scholar
  6. 6.
    Conti, V., Rundo, L., Militello, C., Mauri, G., Vitabile, S.: Resource-efficient hardware implementation of a neural-based node for automatic fingerprint classification. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 8(4), 19–36 (2017). Scholar
  7. 7.
    Harilal, A., et al.: The wolf of SUTD (TWOS): a dataset of malicious insider threat behavior based on a gamified competition. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 9(1), 54–85 (2018). Scholar
  8. 8.
    Ho, J., Kang, D.K.: Mini-batch bagging and attribute ranking for accurate user authentication in keystroke dynamics. Pattern Recognit. 70, 139–151 (2017). Scholar
  9. 9.
    Ho, J., Kang, D.: One-class naïve Bayes with duration feature ranking for accurate user authentication using keystroke dynamics. Appl. Intell. 1–18 (2017). Scholar
  10. 10.
    Joyce, R., Gupta, G.K.: Identity authentication based on keystroke latencies. Commun. ACM 33(2), 168–176 (1990). Scholar
  11. 11.
    Killourhy, K.S., Maxion, R.A.: Comparing anomaly-detection algorithms for keystroke dynamics. In: IEEE/IFIP International Conference on Dependable Systems & Networks, pp. 125–134 (2009).
  12. 12.
    Kim, A., Han, G., Seo, S.H.: Secure and usable bio-passwords based on confidence interval. J. Internet Serv. Inf. Secur. (JISIS) 7(1), 14–27 (2017). Scholar
  13. 13.
    Kim, J.S., Pan, S.B.: A study on EMG-based biometrics. J. Internet Serv. Inf. Secur. (JISIS) 7(2), 19–31 (2017). Scholar
  14. 14.
    Kuang, P., Cao, W., Wu, Q.: Preview on structures and algorithms of deep learning. In: International Computer Conference on Wavelet Active Media Technology and Information Processing, pp. 176–179 (2014).
  15. 15.
    Li, X., Qin, Y.: Research on criminal jurisdiction of computer cybercrime. Procedia Comput. Sci. 131, 793–799 (2018). Scholar
  16. 16.
    Park, M., Seo, J., Han, J., Oh, H., Lee, K.: Situational awareness framework for threat intelligence measurement of android malware. J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl. (JoWUA) 9(3), 25–38 (2018). Scholar
  17. 17.
    Pisani, P.H., Lorena, A.C., de Carvalho, A.C.P.L.F: Adaptive approaches for keystroke dynamics. In: International Joint Conference on Neural Networks, pp. 1–8 (2015).
  18. 18.
    Pisani, P.H., Lorena, A.C., De Carvalho, A.C.P.L.F.: Ensemble of adaptive algorithms for keystroke dynamics. In: Brazilian Conference on Intelligent Systems (BRACIS), pp. 310–315, November 2015.
  19. 19.
    Stefan, D., Shu, X., Yao, D.: Robustness of keystroke-dynamics based biometrics against synthetic forgeries. Comput. Secur. 31(1), 109–121 (2012). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations