Google’s computers have solved the company’s own CAPTCHA technology used to detect whether a user is human or a spam bot.
The discovery came about by accident, as Google was developing a system to read street numbers in Street View to locate addresses on Google Maps.
Different CAPTCHA services go about differentiating humans and bots in different ways, for example, distorting and skewing a series of letters to make them too difficult for automated programmes to decipher, but not so difficult that humans can’t make them out.
Researchers have found that Google’s Street View technology can decipher them with 99% accuracy.
In a blog post, Vinay Shet, Google product manager of reCAPTCHA, said: “Translating a street address to an exact location on a map is harder than it seems. To take on this challenge and make Google Maps even more useful, we’ve been working on a new system to help locate addresses even more accurately, using some of the technology from the Street View and reCAPTCHA teams”
CAPTCHA (Completely Automated Public Turing test to tellComputers and Humans Apart) puzzles are designed to tell humans and bots apart on the web for reasons such as minimising spam.
A company that Google bought in 2009, reCAPTCHA, takes a different approach that not only provides the security of a CAPTCHA form, but actually serves another purpose. reCAPTCHA is used to digitise old printed materials such as books.
As part of its research, it has applied the technology it uses for identifying house numbers in Street View to identifying CAPTCHA words.
The reCAPTCHA technology finds and reads street numbers in Street View, and correlates those numbers with existing addresses to pinpoint their exact locations on Google Maps. Google described these findings in a scientific paper at the International Conference on Learning Representations (ICLR).
“In this paper, we show that this system is able to accurately detect and read difficult numbers in Street View with 90 percent accuracy,” Shet added.
Google found that the algorithm can also be used to read CAPTCHA puzzles and it can decipher the hardest distorted text puzzles from reCAPTCHA with over 99 percent accuracy.
“Thanks to this research, we know that relying on distorted text alone isn’t enough. However, it’s important to note that simply identifying the text in CAPTCHA puzzles correctly doesn’t mean that reCAPTCHA itself is broken or ineffective. On the contrary, these findings have helped us build additional safeguards against bad actors in reCAPTCHA.”
Moving forward from the discovery, Google will improve the technology to not only make Google Maps more precise and useful but also to make reCAPTCHA safer and more effective, Shet said.
As a result, Google suggests that answering a distorted image puzzle should not be the only factor used to distinguish a human from a machine.
Read the blog post here
