This is not a real shock to be if I’m perfectly honestly, I only use reCAPTCHA whenever I need a CAPTCHA implementation for anything.<\/p>\n
And well even then, it’s not totally safe as apparently you can farm out your CAPTCHA cracking (those the fail the automated attempts) to India for a few dollars. It does help cut down on sign-ups and bot spam – but it’s certainly not fool proof.<\/p>\n
The report just reinforces my stance proving that 13 out of 15 popular captures could be cracked with automated software.<\/p>\n
Security researchers have discovered the vast majority of text-based anti-spam tests are easily defeated.<\/p>\n
Computer scientists from Stanford University discovered 13 of 15 CAPTCHA schemes from popular websites were vulnerable to automated attacks. The CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) has been used for several years to prevent automated sign-ups to webmail accounts or online forums in order to block spam bots. Surfers are typically asked during a registration process to identify distorted letters as depicted in an image. A variety of other approaches \u2013 including pictures of cats, audio clips and calculus puzzles \u2013 have been applied to the problem over the years.<\/p>\n
Cybercrooks have responded to the challenge posed by CAPTCHAs by devising techniques that typically involve semi-automatically signing up for new accounts, while relying on the human cogs in 21st century sweatshops \u2013 typically located in India \u2013 to solve the CAPTCHA puzzles themselves.<\/p>\n
The Stanford team, by contrast, looked at whether it was possible to fully automate the process of breaking CAPTCHAs. Their techniques including removing deliberately introduced image background noise and breaking text strings into single characters for easier recognition. The team built an automated tool, called Decaptcha, that applied these various tricks. The approach was partially inspired by techniques used to orientate robots in unknown environments.<\/p><\/blockquote>\n
It’s interesting to see an academic take on this subject though as it’s usually the realm of blackhats and hobbyists. I’m sure with a fair bit of science they did an excellent job at removing the ‘noise’ that most CAPTCHA systems tend to add to the image to try and foil automatic solving.<\/p>\n
I’m also glad to see reCAPTCHA once again stood up well to automated cracking, you’d have to rely on the sweatshops to get past that.<\/p>\n
The worst seems to be Authorize.net from VISA – which is surprising and also sad as it’s dealing with banking.<\/p>\n