Text‐based completely automated public turing tests to tell computers and humans apart (CAPTCHAs) have been widely deployed across the Internet to defend against undesirable or malicious bot programmes. In this study, the authors provide a systematic analysis of text‐based CAPTCHAs and innovatively improve their earlier attack on hollow CAPTCHAs to expand applicability to attack all the text CAPTCHAs. With this improved attack, they have successfully broken the CAPTCHA schemes adopted by 19 out of the top 20 web sites in Alexa including two versions of the famous ReCAPTCHA. With success rates ranging from 12 to 88.8% (note that the success rate for Yandex CAPTCHA is 0%), they demonstrate the effectiveness of their attack method. It is not only applicable to hollow CAPTCHAs, but also to non‐hollow ones. As their attack casts serious doubt on the viability of current designs, they offer lessons and guidelines for designing better text‐based CAPTCHAs.

CAPTCHA is now a standard security technology for differentiating between computers and humans, and the most widely deployed schemes are text-based. While many text schemes have been broken, hollow CAPTCHAs have emerged as one of the latest designs, and they have been deployed by major companies such as Yahoo!, Tencent, Sina, China Mobile and Baidu. A main feature of such schemes is to use contour lines to form connected hollow characters with the aim of improving security and usability simultaneously, as it is hard for standard techniques to segment and recognize such connected characters, which are however easy to human eyes. In this paper, we provide the first analysis of hollow CAPTCHAs' robustness. We show that with a simple but novel attack, we can successfully break a whole family of hollow CAPTCHAs, including those deployed by all the major companies. While our attack casts serious doubt on the viability of current designs, we offer lessons and guidelines for designing better hollow CAPTCHAs.