Text-based Captchas have been widely used to deter misuse of services on the Internet. However, many designs have been broken. It is intellectually interesting and practically relevant to look for alternative designs, which is currently an active topic in the research community. In this paper, we motivate the study of Chinese Captchas as an interesting alternative scheme –counterintuitively, it is possible to design Chinese Captchas that are universally usable, even to those who have never studied Chinese language. More importantly, we ask a fundamental question: is the segmentation-resistance principle established for Roman-character based Captchas applicable to Chinese based design? With deep learning techniques, we offer the first evidence that computers do recognize individual Chinese characters well, regardless of distortion levels. This result suggests that many real-world Chinese schemes are insecure, in contrast to common beliefs. This result is also an essential guideline to the design of secure Chinese Captchas, and relevant to Captcha designs based on other large-alphabet languages such as Japanese.
South China University of Technology