AR CAPTCHA: Recognizing robot by augmented reality

Abstract

Summary We propose a novel AR CAPTCHA that first uses Augmented Reality to design CAPTCHA. Users should use their cameras on mobile devices to capture a marker in the 3D physical world or PC screens to find the appropriate angle to recognize each 3D character rendered on the marker in a 3D registration manner, which is very hard for machines or robots to do the same thing. Besides, we add many random 2D characters on the marker to make the state‐of‐the‐art scene text recognition methods fail to recognize the target 3D characters. To ensure availability, we design dual‐channel scenario setting (mobile phone and physical world) that enhances the security level of CAPTCHA and single‐channel scenario setting (mobile phone only) that the gyroscope could be used for our CAPTCHA. The experimental results reveal that the recognition accuracy of machines is nearly 0%, while a human could recognize AR CAPTCHA in only a few seconds.

Style matching CAPTCHA: match neural transferred styles to thwart intelligent attacks

“…Also, Tap-CAPTCHA is compared with audio CAPTCHA based on efficiency, accuracy, user satisfaction, and workload. In augmented Reality CAPTCHA [32], a user is asked to prompt with a specific marker in a 3D physical environment. As the mobile device rotates, the CAPTCHA's position changes.…”