End-To-End Neural Network Based Captcha Recognition

Authors

  • Jusin Jusin
  • Wilbert Harriman Universitas Pelita Harapan
  • Robin Robin Universitas Pelita Harapan

DOI:

https://doi.org/10.19166/isd.v7i2.552

Keywords:

CAPTCHA, Deep Learning, Neural Network, Supervised Learning

Abstract

Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is widely used as a security measure against spam and bot attacks via the Internet. CAPTCHA works by the assumption that it takes human sensory and cognitive skills (that are not present in computers) to successfully identify objects or letters within a noisy graphical environment. In this work, we propose a way to teach machines to recognize CAPTCHAs with deep learning. Our deep learning model uses a Convolutional Neural Network (CNN) encoder to convert CAPTCHA images into vector representations, followed by a Recurrent Neural Network (RNN) decoder to convert vector representations into text. Our model is able to achieve a validation accuracy of 90% after about an hour of training. Code is available at https://github.com/wilbertharriman/tf2-attention-captcha-recognizer.

References

[1] I. GoodFellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA: MIT Press, 2016.
[2] K. Xu, J. Lei, R Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, and Y. Bengio, "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention", Proceedings of Machine Learning Research, 2015.
[3] D. Bahdanau, K. Cho and Y. Bengio, "Neural Machine Translation by Jointly Learning to Align and Translate", arxiv, Cornell University, 1409.0473v7, 2016.
[4] A. Krizhevsky, I. Sutskever and G. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", NeurIPS Proceedings, 2012.
[5] "What is teacher forcing" in Towards Data Science. [Online]. Available: https://towardsdatascience.com/what-is-teacher-forcing-3da6217fed1c.

Downloads

Additional Files

Published

2022-07-28

Issue

Vol. 7 No. 2 (2022): Journal Information System Development (ISD)

Section

Artikel

License

Copyright (c) 2022 Journal Information System Development (ISD)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Penulis yang menerbitkan jurnal ini menyetujui persyaratan berikut:

  1. Penulis memiliki hak cipta dan memberikan hak untuk publikasi pertama jurnal dengan karya yang secara simultan dilisensikan di bawah Creative Commons Attribution License yang memungkinkan orang lain untuk berbagi karya dengan pengakuan kepengarangan karya dan publikasi awal dalam jurnal ini.
  2. Penulis dapat membuat perjanjian kontrak tambahan yang terpisah untuk distribusi non-eksklusif versi jurnal yang diterbitkan dari karya tersebut (misalnya, mempostingnya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan atas publikasi awalnya di jurnal ini.
  3. Penulis diizinkan dan didorong untuk memposting karya mereka secara online (misalnya, dalam repositori institusional atau di situs web mereka) sebelum dan selama proses pengajuan, karena dapat menyebabkan pertukaran yang produktif, serta kutipan yang lebih awal dan lebih besar dari karya yang diterbitkan (Lihat Pengaruh Akses Terbuka).