Cybersecurity, Machine Learning, Technology
Breaking CAPTCHA Using Machine Learning in 0.05 Seconds
Machine learning model breaks CAPTCHA systems on 33 highly visited websites. The concept bases on GANs
December 19, 2018, by Roberto Iriondo — Updated May 5, 2020
Everyone despises CAPTCHAs (humans, since bots do not have emotions) — Those annoying images containing hard to read the text, which you have to type in before you can access or do “something” online. CAPTCHAs (Completely Automated Public Turing tests to tell Computers and Humans Apart) were developed to prevent automatized programs from being mischievous (filling out online forms, accessing restricted files, accessing a website an incredible amount of times, and others) on the world wide web, by verifying that the end-user is “human” and not a bot. Nevertheless, several attacks on CAPTCHAs have been proposed in the past, but none has been as accurate and fast as the machine learning algorithm presented by a group of researchers from Lancaster University, Northwest University, and Peking University showed below.
One of the first known people to break CAPTCHAs was Adrian Rosebrock, who, in his book “Deep Learning for Computer Vision with Python,”  Adrian goes through how he bypassed the CAPTCHA systems on the E-ZPass New York website using machine learning, where he used deep learning to train his model by downloading a large image dataset of CAPTCHA examples in order to break the CAPTCHA systems.
The main difference between Adrian’s solution and the solution from the research scientists from Lancaster, Northwest, and Peking, is that the researchers did not need to download a large dataset of images to break the CAPTCHAs system, au contraire, they used the concept of a generative adversarial network (GAN) to create synthesized CAPTCHAs, along with a small dataset of real CAPTCHAs to create an extremely fast and accurate CAPTCHA solver.
Generative adversarial networks, introduced by Ian Goodfellow along with other researchers , are deep neural net architectures comprised of two neural networks, which compete against the other in a zero-sum game  to synthesize superficially authentic samples. These are especially useful in scenarios where the model does not have access to a large dataset.
The researchers evaluated their approach by applying 33 text-based CAPTCHA schemes, 11, which are currently being used by 32 of the world’s most popular websites ranked by Alexa. Including CAPTCHA schemes being used by Google, Microsoft, eBay, Wikipedia, Baidu, and many others. The machine learning model used to attack these CAPTCHA systems only needed 500 non-synthesized CAPTCHAs instead of millions of examples as other attacks before this one (such as Adrian’s) have proposed.
Once the model was initialized with the CAPTCHAs security parameters in mind shown in Figure 2, it was used to generate a batch of synthetic CAPTCHAs to train the synthesizer with the 500 real CAPTCHAs obtained from the various CAPTCHA schemes shown in Figure 3. The researchers used 20,000 CAPTCHAs to train the pre-processing model along 200,000 synthetic CAPTCHAs to train the base solver.
The machine learning prototype was implemented using Python. The pre-processing model is built using the Pix2Pix framework, which was implemented using Tensorflow. The fine-tuned solver was coded using Keras. 
After the generative adversarial networks were trained by using the synthesized and real CAPTCHA samples, the CAPTCHA solver was used then to solve CAPTCHAs from highly visited websites, such as Megaupload, Blizzard, Authorize, Captcha.net, Baidu, QQ, reCaptcha, Wikipedia, and others. The unique approach of this method is that most of the sites CAPTCHAs were solved with over 80% success rate, exceeding 95% on sites like Blizzard, Megaupload and Authorize.net, an attack method that has proven to have better accuracy on all other prior methods to solve CAPTCHAs, which used sizeable non-synthesized training datasets.
Other than enhanced accuracy, the researchers mentioned on their paper that their approach was not only more accurate, but also more efficient, and less expensive to implement that other methodologies proposed . Besides being the first GAN based solution for text-based CAPTCHAs, it is an open door for attackers to use, hence their effectiveness and inexpensiveness to implement.
Nevertheless, the approach has some limitations, such as the use of CAPTCHAs with variable numbers of characters. The current approach uses a fixed number of characters — if it’s extended, the prototype breaks. Another, is the use of variable characters on the CAPTCHA, while the prototype can be trained to support this change, it currently does not as is.
It is crucial for highly visited websites to use more robust ways to protect their systems, such as bot-detection measures, cyber-security diagnoses, and analytics, along with multiple layers of security such as device location, types, browsers, and others. — as they are now and even easier target to attack.
DISCLAIMER: The views expressed in this article are those of the author(s) and do not represent the views of Carnegie Mellon University, nor other companies (directly or indirectly) associated with the author(s). These writings are not intended to be final products, yet rather a reflection of current thinking, along with being a catalyst for discussion and improvement.
I. Best Datasets for Machine Learning and Data Science
II. AI Salaries Heading Skyward
III. What is Machine Learning?
IV. Best Masters Programs in Machine Learning (ML) for 2020
V. Best Ph.D. Programs in Machine Learning (ML) for 2020
VI. Best Machine Learning Blogs
VII. Key Machine Learning Definitions
VIII. Breaking Captcha with Machine Learning in 0.05 Seconds
IX. Machine Learning vs. AI and their Important Differences
X. Ensuring Success Starting a Career in Machine Learning (ML)
XI. Machine Learning Algorithms for Beginners
XII. Neural Networks from Scratch with Python Code and Math in Detail
XIII. Building Neural Networks with Python
 Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach | Guixin Ye, Zhanyong Tang, Dingyi Fang, Zhanxing Zhu, Yansong Feng, Pengfei Xu, Xiaojiang Chen, Zheng Wang | Lancaster University, Northwest University, Peking University | https://www.lancaster.ac.uk/staff/wangz3/publications/ccs18.pdf
 Generative Adversarial Networks | Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio | Department of Computer Science and Operations Research, University of Montreal | https://arxiv.org/pdf/1406.2661.pdf
 Zero-Sum Games | Game Theory | Stanford University | https://cs.stanford.edu/people/eroberts/courses/soco/projects/1998-99/game-theory/zero.html
 Deep Learning for Computer Vision with Python | Adrian Rosebrock | https://www.pyimagesearch.com/deep-learning-computer-vision-python-book/
 Gao, H., Tang, M., Liu, Y., Zhang, P., and Liu, X. Research on the security of Microsoft’s two-layer captcha. IEEE Transactions on Information Forensics & Security 12, 7 (2017), 1671–1685
 Gao, H., Wei, W., Wang, X., Liu, X., and Yan, J. The robustness of hollow captchas. In ACM Sig | https://www.lancaster.ac.uk/staff/yanj2/ccs13.pdf
 Mohamed, M., Sachdeva, N., Georgescu, M., Gao, S., Saxena, N., Zhang, C., Kumaraguru, P., Oorschot, P. C. V., and Chen, W. B. A three-way investigation of a game-captcha: automated attacks, relay attacks, and usability. In ACM Symposium on Information, Computer and Communications Security (2014), pp. 195–206
 Yan, J., and Ahmad, A. S. E. A low-cost attack on a Microsoft captcha. In ACM Conference on Computer and Communications | http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.295.9469&rep=rep1&type=pdf