Human-artificial intelligence approaches for secure analysis in CAPTCHA codes

Abstract CAPTCHA ( Completely Automated Public Turing test to tell Computers and Humans Apart ) has long been used keep automated bots from misusing web services by leveraging human-artificial intelligence (HAI) interactions distinguish whether the user is a human or computer program. Various schemes have proposed over years, principally increase usability security against emerging hackers performing malicious operations. However, attacks effectively cracked all common conventional schemes, majority of present methods are also vulnerable human-assisted relay attacks. Invisible reCAPTCHA some approaches not yet cracked. with introduction fourth-generation accurately mimicking behavior, secure would be hardly designed without additional special devices. Almost cognitive-based CAPTCHAs sensor support compromised they still due having limited number challenges can only solved using trusted Obviously, an advantage other in race In this study, as strong starting point for creating future usable we offered overview analysis HAI between users computers under aspects open problems, difficulties, opportunities current schemes.