Advanced graphical-based security approach to handle hard AI problems based on visual security

Abstract

Security is the main aspect to explore human data from different web oriented applications present in artificial intelligence (AI). It is very difficult to use different web applications without security to access data in various places. So that various types of security related approaches were introduced to use services in securely in outside environment, but they have some limitations to protect data from outside attackers (hackers). So that in this paper, we propose and introduce a novel and advanced security model to provide security from outside attackers in AI related web oriented applications. In this approach, we follow the basic features related to Captcha as a graphical password to enable security services in our proposed approach. Using Captcha graphical passwords in our approach, we describe pushing attacks, pass-on attacks and guessing attacks in web applications with random selection of Captcha passwords to use web services. Our experimental results show efficient security relations when compare to existing security approaches in terms of Captcha generation, time and other parameters present in web security applications.