iStockphoto
For anyone out there who somehow doubts that the robot revolution isn’t coming and coming soon, here’s one more bit of evidence that might convince you.
Robots are better at proving they’re human than humans are when it comes to those “I’m not a robot” CAPTCHA tests you see online.
According to a new study recently published on preprint server arXiv, not only are robots better at beating online CAPTCHA tests designed to prove that they aren’t, in fact, human, they’re faster at doing it than humans are.
CAPTCHA, by the way, stands for Completely Automated Public Turing test to tell Computers and Humans Apart.
Unfortunately, since that test was invented in 1997, artificial intelligence has little problem breaking the code even though CAPTCHA has become more and more advanced over the years.
“We do know for sure that they [the tests] are very much unloved. We didn’t have to do a study to come to that conclusion,” Gene Tsudik at the University of California, Irvine told New Scientist. “But people don’t know whether that effort, that colossal global effort that is invested into solving CAPTCHAs every day, every year, every month, whether that effort is actually worthwhile.”
The researchers scoured the world’s 200 most popular websites and found that 120 of them used CAPTCHA tests. They then recruited 1000 people online of varied age, sex, location and educational level to each take 10 CAPTCHA tests on these sites. Their findings showed that the various bots coded by researchers and published in journals tended to beat humans in accuracy and speed.
When humans solved distorted text CAPTCHA tests, for instance, they took between 9 and 15 seconds and achieved accuracy of only 50 to 84 per cent. Bots taking the same test completed it in less than a second with 99.8 per cent accuracy.
Of those 200 websites, Google’s reCAPTCHA was the most commonly used test. (Which Google has used to improve its AI research by doing things like helping Google Books digitize texts or detect house numbers for Google Street View… for free.)
“There’s no easy way using these little image challenges or whatever to distinguish between a human and a bot anymore,” said Gene Tsudik’s research colleague Andrew Searles.