Affiliation:
1. Shah Abdul Latif University
2. Government Girls Degree College
Abstract
Abstract
CAPTCHAs are ubiquitously found on the web these days. It is most commonly used security mechanism against bots. Numerous design variants of static text-based CAPTCHAs were proposed and implemented on the internet over the years. However due to advancements in machine learning and image processing techniques they were proved vulnerable against automated attacks. In this research a new and robust animated CAPTCHA scheme is presented which is based on human’s natural vision capabilities. The newly designed CAPTCHAs are user friendly for humans but extremely hard for bots. The security and usability is kept in mind while designing these CAPTCHAs. Various types of characters, patterns and filters are used to protect them against automated attacks. Overall, 20 types of animated CAPTCHAs are designed in this work. Further in this research, a group of participants have evaluated the usability of newly designed CAPTCHAs and solved with an average success rate of 76.85%. The analysis has proved that the proposed scheme is very much usable for humans and extremely difficult for bots.
Publisher
Research Square Platform LLC
Reference21 articles.
1. Telling humans and computers apart automatically. Communications of the ACM;Ahn L;ACM New York. NY USA,2004
2. Chow Y, Susilo W and Thorncharoensri P (2019) CAPTCHA design and security issues. Advances in Cyber Security: Principles, Techniques, and Applications. Springer, pp. 69–92. https://doi.org/10.1007/978-981-13-1483-4_4
3. Creo.Group. (2012) HelloCAPTCHA vs Spambots. Available at: http://www.hellocaptcha.com (Accessed: 26 January 2023).
4. Shah S S A, Shaikh R A and Arain R H (2018) Reading the Moving Text in Animated Text-Based CAPTCHAs. International Journal of Advanced Computer Science and Applications, Vol. 9, No. 12, 2018. https://doi.org/10.14569/IJACSA.2018.091209
5. Computing Machinery and Intelligence;Turing AM;Mind,1950