Friday, March 03, 2017

ReBreakCaptcha – How to breaking Google’s ReCaptcha v2 using Google’s APIs

East-Ee Security proposed a proof of concept bypass of the Google’s reCaptcha V2 verification system dubbed ReBreakCaptcha. The PoC uses the Google web-based tools for its purpose. According to the author, ReBreakCaptcha “lets you easily bypass Google’s reCaptcha v2 anywhere on the web.”
The CAPTCHA (Completely Automated Procedures for Telling Computers and Humans Apart) service was devised to defeat bots and scripts that can be used to register thousands of accounts at a time.  ReCaptcha is the CAPTCHA solution proposed by Google that leverages image, audio or text challenges to verify the presence of a human while accessing the online service.


The ReBreakCaptcha is able to byPass reCaptcha V2 via a script that leverages Google APIs to capture audio challenges as sound files.
The ReBreakCaptcha works in three stages:
  1. Audio Challenge – Getting the correct challenge type.
  2. Recognition – Converting the audio challenge audio and sending it to Google’s Speech Recognition API.
  3. Verification – Verifying the Speech Recognition result and bypassing the ReCaptcha.
The ReBreakCaptcha technique uses a way to get an audio challenge as part of the reCaptcha process.

“Some of you may notice that instead of an audio challenge, sometimes you get a text challenge,” reads the blog post published by the East-Ee Security researcher. “To bypass it and get an audio challenge, you simply click the ‘Reload Challenge’ button until you get the correct type.”
Once the ‘get an audio challenge’ option is selectes the reCaptcha allows the users to either play the audio file from the web page or download it.
“Let’s download the audio file and send it to Google Speech Recognition API. Before doing so, we will convert it to a ‘wav’ format, which is requested by Google’s Speech Recognition API. Now we have the audio challenge file and are ready to send it to Google Speech Recognition. How can this be done? Using (Google’s own) API,” continues the post.
Then the author sends the audio to the Speech Recognition that turns back the results in text format.
“We will send the ‘wav’ audio file and the Speech Recognition will send us back the result in a string (e.g. ‘25143’). This result will be the solution to our audio challenge,” East-Ee Security explains.
If you are interested in the ReBreakCaptcha technique, give a look at the Python-based proof of concept script available on GitHub.

0 comments:

Post a Comment