Abstract
While most of the existing works have investigated the recognition of a fixed-length CAPTCHA, the authors of the article propose to apply knowledge distillation to approximate the predictions of recurrent convolutional neural networks. Such models have proven themselves well in predicting the dynamic length of characters in images. The paper studies the influence of the size and complexity of the training sample on the quality of recognition. The authors studied the effect of individual color channels and their linear combination on the final quality of models. An estimate of the importance of each color channel was acquired using the trainable scalar coefficients in a linear combination. The results obtained made it possible to reduce the size of the input data for recognition without loss in quality of recognition, as well as speed up the training of the model. The analysis of model errors allowed us to offer suggestions for improving ways of countering automatic recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ba, L.J., Caruana, R.: Do deep nets really need to be deep? arXiv preprint arXiv:1312.6184 (2013)
Burdakov, A.V., Ukharov, A.O., Myalkin, M.P., Terekhov, V.I.: Forecasting of Influenza-like illness incidence in Amur Region with neural networks. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds.) NEUROINFORMATICS 2018. SCI, vol. 799, pp. 307–314. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-01328-8_37
Eroshenkova, D.A., Terekhov, V.I., Khusnetdinov, D.R., Chumachenko, S.I.: Automated determination of forest-vegetation characteristics with the use of a neural network of deep learning. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds.) NEUROINFORMATICS 2019. SCI, vol. 856, pp. 295–302. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-30425-6_34
Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)
Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369–376 (2006)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)
Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on 14(8), 2 (2012)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Hussain, R., Gao, H., Shaikh, R.A.: Segmentation of connected characters in text-based captchas for intelligent character recognition. Multimedia Tools Appl. 76(24), 25547–25561 (2017)
Klopfenstein, L.C., Delpriori, S., Malatini, S., Bogliolo, A.: The rise of bots: a survey of conversational interfaces, patterns, and paradigms. In: Proceedings of the 2017 Conference on Designing Interactive Systems, pp. 555–565 (2017)
Kushchuk, D.O., Ryndin, M.A., Yatskov, A.K., Varlamov, M.I.: Using domain adversarial learning for text captchas recognition. Proc. Inst. Syst. Program. RAS 32(4), 203–216 (2020)
Li, C., Chen, X., Wang, H., Wang, P., Zhang, Y., Wang, W.: End-to-end attack on text-based captchas based on cycle-consistent generative adversarial network. Neurocomputing 433, 223–236 (2021)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Stark, F., Hazırbas, C., Triebel, R., Cremers, D.: Captcha recognition with active deep learning. In: Workshop New Challenges in Neural Computation, vol. 2015, p. 94. Citeseer (2015)
Thobhani, A., Gao, M., Hawbani, A., Ali, S.T.M., Abdussalam, A.: Captcha recognition using deep learning with attached binary images. Electronics 9(9), 1522 (2020)
von Ahn, L., Blum, M., Hopper, N.J., Langford, J.: CAPTCHA: using hard AI problems for security. In: Biham, E. (ed.) EUROCRYPT 2003. LNCS, vol. 2656, pp. 294–311. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-39200-9_18
Wang, J., Qin, J.H., Xiang, X.Y., Tan, Y., Pan, N.: Captcha recognition based on deep convolutional neural network. Math. Biosci. Eng. 16(5), 5851–5861 (2019)
Ye, G., et al.: Yet another text captcha solver: a generative adversarial network based approach. In: Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, pp. 332–348 (2018)
Zhao, B., et al.: Towards evaluating the security of real-world deployed image captchas. In: Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security, pp. 85–96 (2018)
Zhong, Z., Jin, L., Xie, Z.: High performance offline handwritten Chinese character recognition using GoogleNet and directional feature maps. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 846–850. IEEE (2015)
Zi, Y., Gao, H., Cheng, Z., Liu, Y.: An end-to-end attack on text captchas. IEEE Trans. Inf. Forensics Secur. 15, 753–766 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Terekhov, V., Chernenky, V., Ishkov, D. (2022). Text CAPTCHA Traversal via Knowledge Distillation of Convolutional Neural Networks: Exploring the Impact of Color Channels Selection. In: Burnaev, E., et al. Recent Trends in Analysis of Images, Social Networks and Texts. AIST 2021. Communications in Computer and Information Science, vol 1573. Springer, Cham. https://doi.org/10.1007/978-3-031-15168-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-15168-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15167-5
Online ISBN: 978-3-031-15168-2
eBook Packages: Computer ScienceComputer Science (R0)