New machine learning algorithm breaks text CAPTCHAs easier than ever

ZDNet

Academics from UK and China have developed a new machine learning algorithm that can break text-based CAPTCHA systems with less effort, faster, and with higher accuracy than all previous methods. This new algorithm -developed by scientists from Lancaster University (UK), Northwest University (China), and Peking University (China)- is based on the concept of GAN, which stands for "Generative Adversarial Network." GANs are a special class of artificial intelligence algorithms that are useful in scenarios where the algorithm doesn't have access to large quantities of training data. Classing machine learning algorithms usually require millions of data points to train the algorithm in performing a task with the desired degree of accuracy. A GAN algorithm has the advantage that it can work with a much smaller batch of initial data points.


AI Can Easily Break Text CAPTCHA

#artificialintelligence

A new study suggests that text-based CAPTCHAs are no longer safe. Researchers from Northwest University and Peking University in China, and Lancaster University in the U.K., say they developed a machine learning algorithm that can crack most text-based CAPTCHAs within 0.05 seconds. Northwest University's Fang Dingyi said the algorithm exhibited a more than 50% success rate on decoding text-based CAPTCHA schemes used by 50 popular websites within that timeframe. The tool uses a generative adversarial network that teaches a CAPTCHA generator program to produce large numbers of CAPTCHAs to train a solver. Said Fang, "This research suggests one can easily launch an attack on a new CAPTCHA scheme using [artificial intelligence]. It means that this first defense of many websites is no longer reliable."


Google does away with time consuming 'captcha' codes on websites

Daily Mail

Google is doing away with the time consuming tests on websites that ask you to verify you're not a robot. Captcha codes - which ask you to identify words or pictures - are designed to tell the difference between man and machine. The launch of Google's recaptcha v3 means users will no longer need to type in codes or tick boxes as the system will pick up suspicious traffic by itself. Google is doing away with the time consuming tests on websites that ask you to verify that you are a real person. Captcha (Completely Automated Public Turing test to tell Computers and Humans Apart) has become the standard term for simple human-or-robot tests.


Hacking Google reCAPTCHA v3 using Reinforcement Learning

arXiv.org Artificial Intelligence

We present a Reinforcement Learning (RL) methodology to bypass Google reCAPTCHA v3. We formulate the problem as a grid world where the agent learns how to move the mouse and click on the reCAPTCHA button to receive a high score. We study the performance of the agent when we vary the cell size of the grid world and show that the performance drops when the agent takes big steps toward the goal. Finally, we used a divide and conquer strategy to defeat the reCAPTCHA system for any grid resolution. Our proposed method achieves a success rate of 97.4% on a 100x100 grid and 96.7% on a 1000x1000 screen resolution.


Artificial intelligence fools security

#artificialintelligence

Computer scientists have developed artificial intelligence that can outsmart the Captcha website security check system. Captcha challenges people to prove they are human by recognising combinations of letters and numbers that machines would struggle to complete correctly. Researchers developed an algorithm that imitates how the human brain responds to these visual clues. The neural network could identify letters and numbers from their shapes. The research, conducted by Vicarious - a Californian artificial intelligence firm funded by Amazon founder Jeff Bezos and Facebook's Mark Zuckerberg - is published in the journal Science.