Computers will soon be better than you at solving CAPTCHAs

Posted on Friday, October 27 2017 @ 12:43 CEST by Thomas De Maesschalck
The CAPTCHA started out as a simple test to verify whether web services are dealing with a human or an automated script. In the beginning, CAPTCHAs featured a couple of easy to read numbers and/or letters but these days they've become so complicated that most humans require several attempts to get them right.

In the ultimate irony, it looks like computers are now getting better at solving CAPTCHAs than humans. ARS Technica reports researchers from Bay Area startup Vicarious AI crafted a new algorithm that can easily handle CAPTCHAs as well as general text recognition. The new algorithm was modeled after how mammalians process images in their visual cortex.
The remarkable thing about the training is its efficiency. When the authors decided to tackle reCAPTCHAs, they simply compared some examples to the set of fonts available on their computer. Settling on the Georgia font as a reasonable approximation, they showed RCN five examples each of partial rotations for all the upper and lower case letters. At a character level, this was enough to provide over 94 percent letter recognition accuracy. That added up to solving the reCAPTCHA two-thirds of the time. Human accuracy stands at 87 percent, and the system is considered useless from a security standpoint if software can manage it with a one percent accuracy.


About the Author

Thomas De Maesschalck

Thomas has been messing with computer since early childhood and firmly believes the Internet is the best thing since sliced bread. Enjoys playing with new tech, is fascinated by science, and passionate about financial markets. When not behind a computer, he can be found with running shoes on or lifting heavy weights in the weight room.



Loading Comments