"Researchers Fool reCAPTCHA With Google's Own Speech-To-Text Service"

CAPTCHA is a security system widely used on the internet to protect websites against automated bots by generating image, audio, or text challenges. These challenges help distinguish human input from machine input. Researchers have attempted to break this system using reverse-image searchers, deep learning, and experimental neuroscience. Now, researchers at the University of Maryland (UMD) have developed a CAPTCHA-fooling method called unCAPTCHA, which is claimed to be capable of fooling Google's reCAPTCHA, one of the most popular systems used by thousands of websites, with a significantly high success rate. The researchers' unCAPTCHA method uses Google's free speech-to-text service against Google's own CAPTCHA system. This article continues to discuss the concept of the CAPTCHA system, the unCAPTCHA method developed by UMD researchers to break Google's reCAPTCHA, and Google's response to this new hack.

Motherboard reports "Researchers Fool reCAPTCHA With Google's Own Speech-To-Text Service"