Attack-filtered interactive arabic CAPTCHAs

Abstract

A CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) is widely used challenge–response test intended to distinguish between a human user and a malicious bot. This paper deals with text-based interactive CAPTCHA generation. Solving a CAPTCHA is interactive in the sense that the user is asked to solve a challenge from a pool of challenges. The novelty of the proposed method is that we introduce the concept of attack-filtering as a pre-release step for CAPTCHAs. In other words, the distortion level and challenge type for a particular CAPTCHA image are selected in a way that enables the presented CAPTCHA to withstand certain attacks. In addition, attack-filtering enables us to select an appropriate distortion level, present challenges in the proper order, and apply security thresholds. We implemented the presented model in a novel Arabic handwritten text-based interactive CAPTCHA scheme. The experimental results show that, with an interactive challenge pool, the proposed scheme can attain high usability even after filtering the CAPTCHA sample with pre-set bot attacks.