Home > Research > Publications & Outputs > A security analysis of automated Chinese turing...

Electronic data

Links

Text available via DOI:

View graph of relations

A security analysis of automated Chinese turing tests

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

A security analysis of automated Chinese turing tests. / Algwil, Abdalnaser; Ciresan, Dan; Liu, Beibei et al.
ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications: ACSAC 32. New York: ACM, 2016. p. 520-532.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Algwil, A, Ciresan, D, Liu, B & Yan, J 2016, A security analysis of automated Chinese turing tests. in ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications: ACSAC 32. ACM, New York, pp. 520-532. https://doi.org/10.1145/2991079.2991083

APA

Algwil, A., Ciresan, D., Liu, B., & Yan, J. (2016). A security analysis of automated Chinese turing tests. In ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications: ACSAC 32 (pp. 520-532). ACM. https://doi.org/10.1145/2991079.2991083

Vancouver

Algwil A, Ciresan D, Liu B, Yan J. A security analysis of automated Chinese turing tests. In ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications: ACSAC 32. New York: ACM. 2016. p. 520-532 doi: 10.1145/2991079.2991083

Author

Algwil, Abdalnaser ; Ciresan, Dan ; Liu, Beibei et al. / A security analysis of automated Chinese turing tests. ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications: ACSAC 32. New York : ACM, 2016. pp. 520-532

Bibtex

@inproceedings{0a22eeecfd5d4fbe8df1384040ab3c72,
title = "A security analysis of automated Chinese turing tests",
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 Japanese.",
author = "Abdalnaser Algwil and Dan Ciresan and Beibei Liu and Jeff Yan",
year = "2016",
month = dec,
day = "5",
doi = "10.1145/2991079.2991083",
language = "English",
isbn = "9781450347716",
pages = "520--532",
booktitle = "ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications",
publisher = "ACM",

}

RIS

TY - GEN

T1 - A security analysis of automated Chinese turing tests

AU - Algwil, Abdalnaser

AU - Ciresan, Dan

AU - Liu, Beibei

AU - Yan, Jeff

PY - 2016/12/5

Y1 - 2016/12/5

N2 - 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 Japanese.

AB - 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 Japanese.

U2 - 10.1145/2991079.2991083

DO - 10.1145/2991079.2991083

M3 - Conference contribution/Paper

SN - 9781450347716

SP - 520

EP - 532

BT - ACSAC '16 Proceedings of the 32nd Annual Conference on Computer Security Applications

PB - ACM

CY - New York

ER -