Research Trends on CAPTCHA: A Systematic Literature Review
Emmanuel Olufemi Igbekele, Ayodele Ariyo Adebiyi · International Journal of Electrical and Computer Engineering (IJECE) · 2021
The advent of Internet technology has crept into virtually all sectors of the economy and this have culminated in automated processes which makes use of the Internet in executing various tasks and actions. Web Services have now become the trend when it comes to providing solutions to mundane tasks. However, this development comes with the bottleneck of authenticity and intent of users of such services. Providers of these Web services, whether as a Platform, as a Software or as an Infrastructure use various Human Interaction Proof’s (HIPs) to validate authenticity and intent of its users. To prove to a human that you are a human cannot be that hard, it only requires physical or intellectual discuss or gestures to ascertain such, but to prove to a computer that you are human can be an assiduous task. It will require a form of test that human can take, the computer can grade and with that make decisions on intent and validity of user. Completely Automated Public Turing test to tell Computer and Human Apart (CAPTCHA) has been a very beneficial service as a form of Intrusion Detection Systems in Web Services. CAPTCHAs are a class of HIPs that are difficult for computer programs (commonly called bots) to pass but readily easy for humans to take. Majority of the Web services in use today have CAPTCHAs as a defense mechanism against automated bots and indeed any other undue interaction. However, CAPTCHAs keep evolving as more and more research is being carried out to ensure the purpose of CAPTCHA (easy for human to solve while difficult for bots) is not defeated. Research into CAPTCHA can be categorized into two (2) main segment – CAPTCHA development and CAPTCH recognition (solution). In recent years, Selective Learning and Convolutionary Neural Networks (CNN) as well as Deep Convolutionary Neural Network (DCNN) have become emerging trends in both the development and recognition of CAPTCHAs. This paper therefore reviews critically over fifty articles publications that shows the current trends in the area of the CAPTCHA scheme, its development and recognition mechanisms and the way forward in helping to ensure a robust and yet secure CAPTCHA development in guiding future research endeavor in the subject domain.