A security analysis of automated chinese turing tests
Authors:
Open Access
- 5 December 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 520-532
Abstract
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 are currently a topic of active research. We motivate the study of Chinese Captchas as an interesting alternative design - 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 designs? With deep learning techniques, we offer the first evidence that computers do recognize individual Chinese characters well, regardless of distortion levels. This suggests that many real-world Chinese schemes are insecure, in contrast to common beliefs. Our result offers an essential guideline to the design of secure Chinese Captchas, and it is also applicable to Captchas using other large-alphabet languages such as JapaneseKeywords
This publication has 17 references indexed in Scilit:
- A Simple Generic Attack on Text Captchas2016
- Hacking Chinese Touclick CAPTCHA by Multi-Scale Corner Structure Model with Fast Pattern Matching2014
- A three-way investigation of a game-CAPTCHA2014
- ICDAR 2013 Chinese Handwriting Recognition Competition2013
- New CAPTCHA for smartphones and tablet PC2012
- Text-based CAPTCHA strengths and weaknesses2011
- CAPTCHA Design: Color, Usability, and SecurityIEEE Internet Computing, 2011
- Drawing CAPTCHA2006
- Designing human friendly human interaction proofs (HIPs)2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998