American startup has developed a neural network that recognizes popular CAPTCHA with an accuracy of more than 90%
The technology startup Vicarious announced the development of a solution to successfully pass modern CAPTCHA tests , including the most popular reCAPTCHA on the modern Internet, acquired by Google in 2009.
With the help of machine learning and the use of the principles of the structure of the human brain, the researchers managed to achieve 90% recognition accuracy CAPTCHA from Google, Yahoo, PayPal, Captcha.com and other projects. This progress shows that modern CAPTCHAs are no longer effective as a Turing test .
According to Vicarious co-founder Scott Phoenix (Scott Phoenix), the system uses minimal computing power and is different from traditional neural networks running on clusters and devouring megawatts of energy, such as IBM Watson. Such results were achieved by creating an architecture as close as possible to the human brain.
')
The developers of his company, who created the algorithm, do not pursue any mercenary goals and do not intend to sell the technology. At the same time, the main idea of ​​the project is to create a “machine that works like a human brain”.
With the help of machine learning and the use of the principles of the structure of the human brain, the researchers managed to achieve 90% recognition accuracy CAPTCHA from Google, Yahoo, PayPal, Captcha.com and other projects. This progress shows that modern CAPTCHAs are no longer effective as a Turing test .
According to Vicarious co-founder Scott Phoenix (Scott Phoenix), the system uses minimal computing power and is different from traditional neural networks running on clusters and devouring megawatts of energy, such as IBM Watson. Such results were achieved by creating an architecture as close as possible to the human brain.
')
The developers of his company, who created the algorithm, do not pursue any mercenary goals and do not intend to sell the technology. At the same time, the main idea of ​​the project is to create a “machine that works like a human brain”.
Recognition accuracy for different types of CAPTCHA:
Source: https://habr.com/ru/post/199446/
All Articles