A Concept of Oblivious CAPTCHA - Fifth-Factor Technology for Practical CAPTCHA Usages

摘要

The CAPTCHA idea (Completely Automated Public Turing test to tell Computers and Humans Apart) is widely used as a HIP (Human Interactive Proof) for distinguishing between humans and computer programs. This is an automated test that humans can pass, but that current computer programs can't pass. Breaking a CAPTCHA generally involves solving a difficult Artificial Intelligence problem. There are demands for new technologies that are stronger against automatic attacks by machines, without making it too hard for humans to pass the test. In this paper, we propose a concept called the Oblivious CAPTCHA, as a fifth-factor technology for practical usages of CAPTCHA. The Oblivious CAPTCHA gives users tasks such as identifying the English alphabetic characters out of a set of mixed alphabetic and non-alphabetic characters, or counting the number of English alphabetic characters in a string. In experiments we found that the Oblivious CAPTCHA was easy for users, because human beings can recognize images of alphabetic characters quickly and accurately, but this is difficult for computers, because OCR techniques tend to misrecognize non-alphabetic characters as though they were alphabetic. This shows our approach is practical.