Captcha challenge is the first line of defense to protect the website against attacks, it challenges to prove that you are the human user.
Google’s ReCaptcha was introduced in 2014 and it is used by the significant number of users and it relies on advanced risk analysis engine and it offers audio and image captcha, here security researchers took audio captcha to attack.
Security researchers from UM present unCaptcha, a low-resource, fully automated attack on Google’s 2017 reCaptcha audio captcha with a high success rate.
We have evaluated unCaptcha using over 450 reCaptcha challenges from live websites, and showed that it can solve them with 85.15% accuracy in 5.42 seconds, on average: less time than it takes to even play the audio challenge! Researchers said.
To attack captcha one should have huge resources but anyway the success rate is very less.Here they provided a low resource attack with a high success rate.
How unCaptcha works – Captcha
It is completely automated, they obtain audio samples and separated into segments for sound bites analysis and uploads to online speech recognization services like (IBM, Google Cloud, Google Speech Recognition, Sphinx, Wit-AI, Bing Speech Recognition).
And once the results are collected then it presents captcha solution.It is capable of locating “I’m not a robot” checkbox and clicks on it.Researchers also published the code of unCaptcha publically in Github.
For mitigations they suggested in broadening the vocabulary of sound bites beyond just digits, adding background noise which makes the segmentation more difficult.
You can get full research paper titled unCaptcha: A Low-Resource Defeat of reCaptcha’s Audio Challenge available to download here.