Slyck Chatbox - And More

Inspired by brain’s visual cortex, new AI utterly wrecks CAPTCHA security

What's happening in the technology world related to software. Please submit stories for this forum here.
Forum rules

Inspired by brain’s visual cortex, new AI utterly wrecks CAPTCHA security

Postby MrFredPFL » Thu Oct 26, 2017 9:32 pm

Story :

Computer algorithms have gotten much better at recognizing patterns, like specific animals or people's faces, allowing software to automatically categorize large image collections. But we've come to rely on some things that computers can't do well. Algorithms can't match their image recognition to semantic meaning, so today you can ensure a human's present by asking them to pick out images of street signs. And algorithms don't do especially well at recognizing when familiar images are distorted or buried in noise, either, which has kept us relying on text-based CAPTCHAs, the distorted text used to verify a human is interacting with Web services.

Or we had relied on them 'til now, at least. In today's issue of Science, a Bay Area startup called Vicarious AI describes an algorithm they created that is able to take minimal training and easily handle CAPTCHAs. It also managed general text recognition. Vicarious' secret? They modeled the structure of their AI on information we've gained from studying how the mammalian visual cortex processes images.

The remarkable thing about the training is its efficiency. When the authors decided to tackle reCAPTCHAs, they simply compared some examples to the set of fonts available on their computer. Settling on the Georgia font as a reasonable approximation, they showed RCN five examples each of partial rotations for all the upper and lower case letters. At a character level, this was enough to provide over 94 percent letter recognition accuracy. That added up to solving the reCAPTCHA two-thirds of the time. Human accuracy stands at 87 percent, and the system is considered useless from a security standpoint if software can manage it with a one percent accuracy.

And it's not just reCAPTCHA. This system managed the BotDetect system with similar accuracy and Yahoo and PayPal systems with 57 percent accuracy. The only differences involved are the fonts used and some hand-tweaking of a few parameters that adjust for the deformations and background noise in the different systems. By contrast, other neural networks have needed on the order of 50,000 solved CAPTCHAs for training compared to RCN's 260 images of individual characters. Those neural networks will typically have to be retrained if the security service changes the length of its string or alters the distortion it uses.

Posts: 15753
Joined: Wed Aug 17, 2005 4:48 pm

Re: Inspired by brain’s visual cortex, new AI utterly wrecks

Postby ejonesss » Fri Oct 27, 2017 12:22 pm

good!!! maybe we will see the captchas removed mainly the recaptchas that require clicking blocks with audio option.

i think admins need to sit monitoring the logs and watch for signs of automation or better yet use some of the nsa exploits and turn on the web cams remotely to see if a human is at the system or ban the accounts that are suspected to automate .

the problem i have is that the captchas dont even work and require repeatedly clicking and even getting new challenges such as switching to street signs or even click the audio challenge only to have the system think i am a robot and blocking the logins.
Posts: 2973
Joined: Thu Feb 06, 2003 5:43 pm

Return to Tech/Software News

Who is online

Users browsing this forum: No registered users and 3 guests

© 2001-2008