Contributors: Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, Zheng Wang Northwest University, China; Lancaster University, UK; Peking University, China

This is an open source code for solving the text-based captchas based on the machine learning technologies. This approach is able to achieve a higher success rate but requires significantly fewer real captchas. Here we exposed partial source code that can run independently for security reasons. Note that it is not production ready. If you encounter any problems, please file an issue on GitHub.

• Linux or Windows

• NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN may work with minimal modification, but untested)

Source code of this repository is released under the Apache License (v2.0)

@inproceedings{ye2018yet,     
  title={Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach},  
  author={Ye, Guixin and Tang, Zhanyong and Fang, Dingyi and Zhu, Zhanxing and Feng, Yansong and Xu, Pengfei and Chen, Xiaojiang and Wang, Zheng},  
  booktitle={The 25th ACM Conference on Computer and Communications Security},     
  series = {CCS '18},     
  year={2018},     
  organization={ACM}    
  }