Adaptive CAPTCHA: A CRNN-Based Text CAPTCHA Solver with Adaptive Fusion Filter Networks
Source abstract
Abstract
Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment; they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive CAPTCHA with a CNN combined with an RNN (CRNN) module and trainable Adaptive Fusion Filtering Networks (AFFN), which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexities show that, compared with the baseline model Deep CAPTCHA, the number of parameters of our proposed model is reduced by about 70%, and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed. Compared with several of the latest models, the model proposed by the study also has better comprehensive performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: User Authentication and Security Systems · Advanced Malware Detection Techniques · Digital Media Forensic Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical Engineering, Universiti Teknologi MARA (UiTM), Shah Alam Selangor 40450, Malaysia
School of Intelligent Manufacturing, Leshan Vocational and Technical College, Leshan 614000, China
Funding
Leshan Vocational and Technical College · Universiti Teknologi MARA
References (53)
Show source-provided references
1. Telling humans and computers apart automatically10.1145/966389.966390 ↗
2. Biham, E. (2003). CAPTCHA: Using Hard AI Problems for Security. Advances in Cryptology—EUROCRYPT 2003, Springer.10.1007/3-540-39200-9 ↗
3. Augmented Data Selector to Initiate Text-Based CAPTCHA Attack10.1155/2021/9930608 ↗
4. Noury, Z., and Rezaei, M. (2020). Deep-CAPTCHA: A deep learning based CAPTCHA solver for vulnerability assessment. arXiv.10.31219/osf.io/km35b ↗
5. Lopresti, D., Hu, J., and Kashi, R. (2002). Human Interactive Proofs and Document Image Analysis. Document Analysis Systems V, Springer.10.1007/3-540-45869-7 ↗
6. Baykara, M., Alnıak, F., and Çınar, K. (2018, January 22–25). Review and comparison of captcha approaches and a new captcha model. Proceedings of the 2018 6th International Symposium on Digital Forensic and Security (ISDFS), Antalya, Turkey.10.1109/ISDFS.2018.8355316 ↗
7. Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms10.1016/j.ifacol.2018.07.155 ↗
8. Towards understanding the security of modern image captchas and underground captcha-solving services10.26599/BDMA.2019.9020001 ↗
9. Research trends on CAPTCHA: A systematic literature
10. UmaMaheswari, P., Ezhilarasi, S., Harish, P., Gowrishankar, B., and Sanjiv, S. (2020, January 10–11). Designing a Text-based CAPTCHA Breaker and Solver by using Deep Learning Techniques. Proceedings of the 2020 IEEE International Conference on Advances and Developments in Electrical and Electronics Engineering (ICADEE), Coimbatore, India.10.1109/ICADEE51157.2020.9368949 ↗
11. Ye, G., Tang, Z., Fang, D., Zhu, Z., Feng, Y., Xu, P., Chen, X., and Wang, Z. (2018, January 15–19). Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach. Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, Toronto, ON, Canada.10.1145/3243734.3243754 ↗
12. Zheng, Y. (2022, January 11–13). Captcha Recognition Based on Attention Mechanism. Proceedings of the 6th International Conference on Control Engineering and Artificial Intelligence, Virtual Event, Japan.10.1145/3522749.3523077 ↗
13. Chen, Y., Luo, X., Xu, S., and Chen, R. (2022, January 28–30). CaptchaGG: A linear graphical CAPTCHA recognition model based on CNN and RNN. Proceedings of the 2022 9th International Conference on Digital Home (ICDH), Guangzhou, China.10.1109/ICDH57206.2022.00034 ↗
14. Xing, W., Mohd, M.R.S., Johari, J., and Ruslan, F.A. (July, January 29). A Review on Text-based CAPTCHA Breaking Based on Deep Learning Methods. Proceedings of the 2023 International Conference on Computer Engineering and Distance Learning (CEDL), Shanghai, China.10.1109/CEDL60560.2023.00040 ↗
15. Zhang, Y., and Zhang, C. (2003, January 9–11). A new algorithm for character segmentation of license plate. Proceedings of the IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683), Columbus, OH, USA.
16. CAPTCHA recognition based on deep convolutional neural network10.3934/mbe.2019292 ↗
17. CAPTCHA Recognition Method Based on CNN with Focal Loss10.1155/2021/6641329 ↗
18. A novel CAPTCHA solver framework using deep skipping Convolutional Neural Networks10.7717/peerj-cs.879 ↗
19. An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition10.1109/TPAMI.2016.2646371 ↗
20. Breaking CAPTCHA with Capsule Networks10.1016/j.neunet.2022.06.041 ↗
21. Position-Encoding Convolutional Network to Solving Connected Text Captcha10.2478/jaiscr-2022-0008 ↗
22. De-CAPTCHA: A novel DFS based approach to solve CAPTCHA schemes10.1016/j.compeleceng.2021.107593 ↗
23. Qing, K., and Zhang, R. (2022, January 22–25). An Efficient ConvNet for Text-based CAPTCHA Recognition. Proceedings of the 2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Penang, Malaysia.10.1109/ISPACS57703.2022.10082852 ↗
24. Breaking CAPTCHA system with minimal exertion through deep learning: Real-time risk assessment on Indian government websites10.1145/3584974 ↗
25. Multiview deep learning-based attack to break text-CAPTCHAs10.1007/s13042-022-01675-8 ↗
26. Derea, Z., Zou, B., Al-Shargabi, A.A., Thobhani, A., and Abdussalam, A. (2023). Deep Learning Based CAPTCHA Recognition Network with Grouping Strategy. Sensors, 23.10.3390/s23239487 ↗
27. Sinha, S., and Surve, M.I. (2023, January 21–23). CAPTCHA Recognition And Analysis Using Custom Based CNN Model—Capsecure. Proceedings of the 2023 International Conference on Emerging Techniques in Computational Intelligence (ICETCI), Hyderabad, India.10.1109/ICETCI58599.2023.10331187 ↗
28. Object Detection in 20 Years: A Survey10.1109/JPROC.2023.3238524 ↗
29. Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). SSD: Single Shot MultiBox Detector. Computer Vision—ECCV 2016, Springer International Publishing.10.1007/978-3-319-46454-1 ↗
30. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
31. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
32. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
33. Captcha recognition based on faster R-CNN10.1007/978-3-319-63312-1_52 ↗
34. A deep learning-based attack on text CAPTCHAs by using object detection techniques10.1049/ise2.12047 ↗
35. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-End Object Detection with Transformers. arXiv.10.1007/978-3-030-58452-8_13 ↗
36. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6–11). Wasserstein Generative Adversarial Networks. Proceedings of the 34th International Conference on Machine Learning, PMLR, Sydney, NSW, Australia.
37. Using Generative Adversarial Networks to Break and Protect Text Captchas10.1145/3378446 ↗
38. Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
39. Make complex CAPTCHAs simple: A fast text captcha solver based on a small number of samples10.1016/j.ins.2021.07.040 ↗
40. Chen, H., Jiang, B., and Chen, H. (2020, January 19–20). StyleCAPTCHA: CAPTCHA Based on Stylized Images to Defend against Deep Networks. Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference, Virtual.10.1145/3412815.3416895 ↗
41. Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence10.1145/3505226 ↗
42. Kimbrough, T., Tian, P., Liao, W., Blasch, E., and Yu, W. (2022, January 2–5). Deep CAPTCHA Recognition Using Encapsulated Preprocessing and Heterogeneous Datasets. Proceedings of the IEEE INFOCOM 2022—IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), New York, NY, USA.10.1109/INFOCOMWKSHPS54753.2022.9798233 ↗
43. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (arXiv, 1807). CBAM: Convolutional Block Attention Module, arXiv.
44. An End-to-End Attack on Text CAPTCHAs10.1109/TIFS.2019.2928622 ↗
45. Shi, Y., Liu, X., Han, S., Lu, Y., and Zhang, X. (2021, January 28–30). A Transformer Network for CAPTCHA Recognition. Proceedings of the 2021 2nd International Conference on Artificial Intelligence and Information Systems, Chongqing, China.10.1145/3469213.3470366 ↗
46. Chan, K.-H., Im, S.-K., Ian, V.-K., Chan, K.-M., and Ke, W. (2020, January 26–29). Enhancement Spatial Transformer Networks for Text Classification. Proceedings of the 4th International Conference on Graphics and Signal Processing, Nagoya, Japan.10.1145/3406971.3406981 ↗
47. Zhao, R., Deng, X., Wang, Y., Yan, Z., Han, Z., Chen, L., Xue, Z., and Wang, Y. (2023, January 21–25). GeeSolver: A Generic, Efficient, and Effortless Solver with Self-Supervised Learning for Breaking Text Captchas. Proceedings of the 2023 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.10.1109/SP46215.2023.10179379 ↗
48. Li, Y., Pan, H., Ye, H., and Zheng, J. (2023, January 3–5). Transformer Encoder for Efficient CAPTCHA Recognize. Proceedings of the 2023 2nd International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE), Chengdu China.10.1109/CBASE60015.2023.10439128 ↗
49. Hallyal, R.A., Sujatha, C., Desai, P., and Meena, S.M. (2023, January 7–9). Optimized Recognition Of CAPTCHA Through Attention Models. Proceedings of the 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), Lonavla, India.10.1109/I2CT57861.2023.10126193 ↗
50. An Experimental Investigation of Text-based CAPTCHA Attacks and Their Robustness
51. Alsuhibany, S.A. (2011, January 22–26). Optimising CAPTCHA Generation. Proceedings of the 2011 Sixth International Conference on Availability, Reliability and Security, Vienna, Austria.10.1109/ARES.2011.114 ↗
52. San Luo (2024, February 05). m-CAPTCHA. Available online: https://www.kaggle.com/datasets/sanluo/mcaptcha.
53. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗