A security analysis of automated Chinese turing tests
A security analysis of automated Chinese turing tests
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 largealphabet languages such as Japanese.
Chinese captcha, Convolutional neural network, Deep neural network, Security, Usability
520-532
Association for Computing Machinery
Algwil, Abdalnaser
12677a15-6eac-44d0-8923-659506671335
Ciresan, Dan
42325073-c46c-42b5-8ac2-4fc5b9ced277
Liu, Beibei
02a7a27e-a3c2-4841-8863-4efd212333b1
Yan, Jeff
a2c03187-3722-46c8-b73b-439eb9d1a10e
5 December 2016
Algwil, Abdalnaser
12677a15-6eac-44d0-8923-659506671335
Ciresan, Dan
42325073-c46c-42b5-8ac2-4fc5b9ced277
Liu, Beibei
02a7a27e-a3c2-4841-8863-4efd212333b1
Yan, Jeff
a2c03187-3722-46c8-b73b-439eb9d1a10e
Algwil, Abdalnaser, Ciresan, Dan, Liu, Beibei and Yan, Jeff
(2016)
A security analysis of automated Chinese turing tests.
In Proceedings - 32nd Annual Computer Security Applications Conference, ACSAC 2016.
vol. 5-9-December-20,
Association for Computing Machinery.
.
(doi:10.1145/2991079.2991083).
Record type:
Conference or Workshop Item
(Paper)
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 largealphabet languages such as Japanese.
This record has no associated files available for download.
More information
Published date: 5 December 2016
Additional Information:
Publisher Copyright:
© 2016 ACM.
Venue - Dates:
32nd Annual Computer Security Applications Conference, ACSAC 2016, , Los Angeles, United States, 2016-12-05 - 2016-12-09
Keywords:
Chinese captcha, Convolutional neural network, Deep neural network, Security, Usability
Identifiers
Local EPrints ID: 500839
URI: http://eprints.soton.ac.uk/id/eprint/500839
PURE UUID: 3f068383-7dd1-4b6a-a71e-7fc7e52493ef
Catalogue record
Date deposited: 13 May 2025 17:24
Last modified: 13 May 2025 17:24
Export record
Altmetrics
Contributors
Author:
Abdalnaser Algwil
Author:
Dan Ciresan
Author:
Beibei Liu
Author:
Jeff Yan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics