Advertisement

Dynamically Weighted Multi-View Semi-Supervised Learning for CAPTCHA

  • Congqing He
  • Li PengEmail author
  • Yuquan Le
  • Jiawei He
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11440)

Abstract

With the development of Optical Character Recognition and artificial intelligence technologies, the security of Behavioral Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) has become an increasingly difficult task. In order to prevent malicious attacks and maintain network security, most existing works on CAPTCHA are to construct a fine binary classifier model but are not yet capable of detecting new attack means during confrontation. This motivates us to propose a Dynamically Weighted Multi-View Semi-Supervised Learning, dubbed as DWMVSSL method, to relieve this problem. More specifically, our proposed method extracts hidden patterns from multiple perspectives and updates the view weighting dynamically which can constantly detect new attack means. In addition, due to existing some redundant feature in views, we design a Filter Artificial Bee Colony method, named as FABC for feature selection which can efficiently reduce the impact of high dimensional features. The experimental results show that, compared the existing representative baseline methods, our DWMVSSL method can effectively detecting new attacks on confrontation.

Keywords

CAPTCHA Semi-supervised learning Multi-view Feature selection 

References

  1. 1.
    Belk, M., Fidas, C., Germanakos, P., et al.: Do human cognitive differences in information processing affect preference and performance of CAPTCHA? Int. J. Hum.-Comput. Stud. 84, 1–18 (2015)CrossRefGoogle Scholar
  2. 2.
    Kwak, N.J., Song, T.S.: Android-based human action recognition alarm service using action recognition parameter and decision tree. Int. J. Secur. Appl. 7(4), 277–286 (2013)Google Scholar
  3. 3.
    Mazaar, H., Emary, E., Onsi, H.: Ensemble based-feature selection on human activity recognition. In: International Conference on Informatics and Systems, pp. 81–87. ACM (2016)Google Scholar
  4. 4.
    Ashfaq, R.A.R., Wang, X.Z., Huang, J.Z., et al.: Fuzziness based semi-supervised learning approach for intrusion detection system. Inf. Sci. Int. J. 378(C), 484–497 (2017)Google Scholar
  5. 5.
    Yu, L., Liu, H.: Eficient feature selection via analysis of relevance and redundancy. J. Mach. Learn. Res. 5(12), 1205–1224 (2004)zbMATHGoogle Scholar
  6. 6.
    Chuang, L.Y., Chang, H.W., Tu, C.J., et al.: Improved binary PSO for feature selection using gene expression data. Comput. Biol. Chem. 32(1), 29–38 (2008)CrossRefGoogle Scholar
  7. 7.
    Karaboga, D., Basturk, B.: A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J. Global Optim. 39(3), 459–471 (2007)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Yu, L., Liu, H.: Feature selection for high-dimensional data: a fast correlation-based filter solution. In: Proceedings of the 20th International Conference on Machine Learning (ICML-03), pp. 856–863 (2003)Google Scholar
  9. 9.
    Xue, B., Zhang, M., Browne, W.N.: Particle swarm optimization for feature selection in classification: a multi-objective approach. IEEE Trans. Cybern. 43(6), 1656 (2013)CrossRefGoogle Scholar
  10. 10.
    Nigam, K., Ghani, R.: Analyzing the effectiveness and applicability of co-training. In: International Conference on Information and Knowledge Management, pp. 86–93. ACM (2000)Google Scholar
  11. 11.
    Zhou, Z.H., Li, M., et al.: Tri-training: exploiting unlabeled data using three classifiers. IEEE Trans. Knowl. Data Eng. 17(11), 1529–1541 (2005)CrossRefGoogle Scholar
  12. 12.
    Li, M., Zhou, Z.H.: Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples. IEEE Press (2007)Google Scholar
  13. 13.
    Zhu, S., Sun, X., Jin, D.: Multi-view semi-supervised learning for image classification. Neurocomputing 208, 136–142 (2016)CrossRefGoogle Scholar
  14. 14.
    Sindhwani, V., Niyogi, P., Belkin, M.: A co-regularization approach to semi-supervised learning with multiple views. In: Proceedings of ICML Workshop on Learning with Multiple Views, pp. 74–79. Citeseer (2005)Google Scholar
  15. 15.
    Bezdek, J.C., Ehrlich, R., Full, W.: FCM: the fuzzy c-means clustering algorithm. Comput. Geosci. 10(2–3), 191–203 (1984)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Computer Science and Electronic EngineeringHunan UniversityChangshaChina

Personalised recommendations