Security Analysis in Graphical Password Schemes

A model is developed to identify the most likely regions for users to click in order to create graphical passwords. A graphical password is a sequence of points, chosen by a user in an image that is displayed on the screen. It allows us to evaluate automatically whether a given image is well suited for the system, and to analyze possible dictionary attacks against the system. Performance was very good in terms of speed, accuracy, and number of errors. Users preferred this and saying that selecting and remembering only one point per image was easier, and that seeing each image triggered their memory of where the corresponding point was located. It provides greater security than others because the number of images increases the workload for attackers.