CaptchAll: An Improvement on the Modern Text-based CAPTCHA
Charlie Obimbo, Andrew Halligan, Patrick De Freitas · Procedia Computer Science · 2013
Current CAPTCHA implementations are a source of frustration for many and yet they are an integral and necessary piece of the World Wide Web, as we know it. This paper intends to propose a solution to this ever-growing problem, CaptchAll, an easy to use and difficult to break image-based CAPTCHA. In this system, image scenes of a complex nature are presented to the user along with a piece of challenge text, asking the user to identify objects in the image with a simple click. While this task is unproblematic for the typical Internet user, it is an incredibly challenging image processing task for an automated program without proper context. Initial in-depth analysis is able to demonstrate the user-friendly nature of the system while outlining the struggle in which automated attackers will face