New AI tool can decode security captchas
Researchers have created a new artificial intelligence tool that can read text captcha schemes used to defend the majority of the worlds most popular websites from cyber attacks The algorithm based on deep learning methods, is the most effective solver captcha security and authentication systems to date and could spell the end for one of the most widely used website security systems
Researchers have created a new artificial intelligence tool that can read text captcha schemes used to defend the majority of the world's most popular websites from cyber attacks. The algorithm based on deep learning methods, is the most effective solver captcha security and authentication systems to date and could spell the end for one of the most widely used website security systems.
Text-based captchas use a jumble of letters and numbers, along with other security features such as occluding lines, to distinguish between humans and malicious automated computer programmes. It relies on people finding it easier to decipher the characters than machines. The tool, developed by Lancaster University in the UK, Northwest University in the US and Peking University in China, delivers significantly higher accuracy than previous captcha attack systems.
It is able to successfully crack versions of captcha where previous attack systems have failed. The solver is also highly efficient. It can solve a captcha within 0.05 of a second by using a desktop PC, researchers said. The method involves teaching a captcha generator programme to produce large numbers of training captchas that are indistinguishable from genuine captchas. These are then used to rapidly train a solver, which is then refined and tested against real captchas.
By using a machine-learned automatic captcha generator the researchers, or would be attackers, are able to significantly reduce the effort, and time, needed to find and manually tag captchas to train their software. It only requires 500 genuine captchas, instead of the millions that would normally be needed to effectively train an attack programme. Previous captcha solvers are specific to one particular captcha variation.
Prior machine-learning attack systems are labour intensive to build, requiring a lot of manual tagging of captchas to train the systems. They are also easily rendered obsolete by small changes in the security features used within captchas. Since, the new solver requires little human involvement it can easily be rebuilt to target new, or modified, captcha schemes.