How humans can help computers to solve an artificial problem?

Abstract

The idea of using CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) was to protect websites from attacks initiated by the automated computer scripts or computer robots (bots). One of the most important issues about CAPTCHAs is that the test has to be designed in a way that makes it too hard or almost impossible for the computer programs to break the test however, at the same time it should be fairly easy for human users to solve. ReCAPTCHA is known as one of the most popular CAPTCHA models which is being used by the majority of well-known websites such as Yahoo!, Google, Facebook and etc. ReCAPTCHA is being used in order to help digitizing old text books and notes. In this paper we investigate the algorithm behind reCAPTCHA more in depth and find out how basically a simple script-based computer program can get use of real human users in order to solve an artificial problem for the machines. We also review some of the most important security accepts of the reCAPTCHA model.