A novel CAPTCHA mechanism: virtual keyboard for robust user authentication

Abstract

In the current digital age, the growing prevalence of cybersecurity threats has heightened the importance of securing online platforms. Completely automated public turing test to tell computers and humans apart (CAPTCHA) mechanisms are commonly employed to protect these platforms from spam, a prevalent type of online identity theft, and to strengthen defenses against automated attacks. This study introduces an innovative method to improve security against such automated threats. A key feature of the proposed system is the implementation of a virtual keyboard, which plays a central role in user authentication. The system utilizes a text recognition algorithm to authenticate users in real-time, effectively minimizing the risk of unauthorized access and ensuring enhanced security. Furthermore, the system is capable of detecting and managing imprecise user inputs, thereby increasing its reliability. Experimental findings highlight the system’s efficacy in mitigating comment spam on blogs, demonstrating its robustness against optical character recognition (OCR)-based attacks. Achieving an 87% success rate in user authentication, the system proves to be a strong defense against automated threats, reinforcing its overall security framework. This study underscores the potential of the proposed approach to advance cybersecurity measures for online platforms.