Provided by: University of North Alabama
Date Added: Jun 2012
The authors explore the robustness and usability of moving-image object recognition (video) captchas, designing and implementing automated attacks based on computer vision techniques. Their approach is suitable for broad classes of moving-image captchas involving rigid objects. They first present an attack that defeats instances of such a captcha (NuCaptcha) representing the state-of-the-art, involving dynamic text strings called code-words. They then consider design modifications to mitigate the attacks (e.g., overlapping characters more closely). They implement the modified captchas and test if designs modified for greater robustness maintain usability. Their lab-based studies show that the modified captchas fail to offer viable usability, even when the captcha strength is reduced below acceptable targets - signaling that the modified designs are not viable.