Abstract
CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is one of the easiest ways to achieve human authentication on the web sites. Text-based CAPTCHAs are the most popular type of CAPTCHA used on the web sites. Most of the text-based CAPTCHAs are successfully recognized. Devanagari CAPTCHAs are also existing but not used on the web sites. In India, mostly web sites are also displaying the information in native languages so that native citizens can use these public web sites. These web sites may use native language CAPTCHA like Devanagari CAPTCHA. The security of Devanagari CAPTCHA is never tested till date. In this paper, 20 unique Devanagari CAPTCHAs are tested from de-noising and segmentation (character segmentation) point of view. All the 20 designs are successfully de-noised and segmented. A high success rate of segmentation is achieved that ranges from 88.14 to 98.06%. The paper proposes benchmarks for developing a secure text CAPTCHA.
Similar content being viewed by others
References
Ahn L, Blum M, Langford J. Telling humans and computers apart automatically. Commun ACM. 2004;47:56–60.
Noar M. Verification of a human in the loop, or identification via the Turing test. 1996.
Coates A, Baird H and Fateman R. Pessimal print: a reverse Turing test. In: Proceedings of international conference on document analyses and recognition, vol 5. 2003. p. 158–63.
Turing AM. Computing machinery and intelligence. Mind. 1950;59:433–60.
Pope C, Kaur K. Is it human or computer? Defending E-commerce with Captchas. IEEE Comput Soc. 2005;7:43–9.
Saikat C, Singhal M. Password-based authentication: preventing dictionary attacks. IEEE Comput Soc. 2007;40:68–74.
Yu J, Ma X, Han T. Usability investigation on the localization of text CAPTCHAs: take Chinese characters as a case study. In: Proceedings of the transdisciplinary engineering—24th ISPE Inc., international conference, vol 5. 2016. p. 233–42.
Algwil A, Ciresanand D, Liu B. A security analyses of automated Chinese Turing tests. In: Proceedings of the 32nd annual conference on computer security applications. 2016. p. 520–32.
Alsuhibany S. Generating Arabic handwritten CAPTCHA for cyber security. Int J Comput Sci Netw Secur. 2018;18:41–7.
Chen J, Luo X, Guo Y. A survey on breaking technique of text-based CAPTCHA. Secur Commun Netw. 2017;2017:1–15.
Cerqueira J, Almeida P, Canedo E, Alves G, Giozza W, Mendonça F, Sousa R. Exploratory overview on breaking CAPTCHAs using the theory of the consolidated meta-analytic approach. In: 15th Iberian conference on information systems and technologies (CISTI). 2020. p. 1–6.
Mori G, Malik J. Recognizing objects in adversarial clutter: breaking a visual CAPTCHA. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, vol 1. 2003. p. 1.
Moy G, Jones N, Harkless C. Distortion estimation techniques in solving visual CAPTCHAs. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, vol 2. 2004. p. 1–6.
Yan Y, Ahmad A. Breaking visual CAPTCHAs with naive pattern recognition algorithms. In: Proceedings of the 23rd annual computer security applications conference. 2007. p. 279–91.
Ahmad A, Yan J. CAPTCHA colour, usability and security. IEEE Internet Comput. 2012;16:1089–7801.
Yan J, Ahmad A. A low-cost attack on a Microsoft CAPTCHA. In: Proceedings of the 15th ACM conference on computer and communications security. 2008. p. 543–54.
Huang S, Lee Y, Bell G. An efficient segmentation algorithm for CAPTCHAs with line cluttering and character warping. Multimed Tools Appl. 2010;48:267–89.
Bursztein E, Martin M, Mitchell J. Text-based CAPTCHA strengths and weaknesses. In: Proceedings of the 18th ACM conference on computer and communications security. 2011. p. 125–38.
Gao H, Wang W, Qi J. The robustness of hollow CAPTCHAs. In: Proceedings of the 2013 ACM SIGSAC conference on computer & communications security. 2013. p. 1075–86.
Bursztein E, Aigrain J, Moscicki A. The end is nigh: generic solving of text-based CAPTCHAs. In: Proceedings of 8th USENIX workshop on offensive technologies (WOOT 14). 2014. p. 1–15.
Bansal A, Garg A, Gupta A, Gupta A. Breaking a visual CAPTCHA: a novel approach using HMM. 2008. p. 1–6.
Nguyen V, Chow Y, Susilo W. On the security of text-based 3D CAPTCHAs. Comput Secur. 2014;45:84–99.
Gao H, Yan J, Cao F. A simple generic attack on text CAPTCHAs. In: Proceedings of network and distributed system security symposium (NDSS). 2016. p. 1–14.
Noury Z, Rezaei M. Deep-CAPTCHA: a deep learning based [CAPTCHA solver for vulnerability assessment. SSRN. 2020;1:1–9.
Dionysiou A, Athanasopoulos E. SoK: machine vs. machine—a systematic classification of automated machine learning-based CAPTCHA Solvers. Comput Secur. 2020;97:101947.
Pal U, Roy P, Tripathy N, Llados J. Multi-oriented Bangla and Devanagari text recognition. Pattern Recognit. 2010;43:4124–36.
Roy P, Pal U, Llados J, Delalandre M. Multi-oriented touching text character segmentation in graphical documents using dynamic programming. Pattern Recognit. 2012;45:1972–83.
Avinash A, Chandavale A, Sapkal A. Security analyses of CAPTCHA. In: Conference paper in communications in computer and information science. 2012.
Ayan B, Abhirup D, Ankan B, Perla K, Pratim R. Handwriting recognition in low-resource scripts using adversarial learning. In: Proceedings of IEEE conference on computer vision and pattern recognition. 2019. p. 4767–76.
Raghunandan K, Palaiahnakote S, Sangheeta R, Hemantha G, Pal U, Lu T. Multi-script-oriented text detection and recognition in video/scene/born digital images. IEEE Trans Circuits Syst Video Technol. 2019;29:1–1.
Partha R, Mohta A, Chaudhuri B. Synthetic data generation for Indic handwritten text recognition. In: Computer vision and pattern recognition. 2018. arXiv:1804.06254.
Acknowledgements
We are thankful to the almighty nature which always guided us when we were losing hope and feeling tired. We are thankful to all the reviewers who helped us in improving the article by giving very valuable suggestions and comments. We are thankful to all the persons who have helped us in collecting the images from the websites. These analyses would have not been possible without collecting a huge database. We have not received any funding assistance from any government and non-government organizations for this research.
Funding
We declare that there is no relationship between this manuscript and any consultancies, stock ownership, honoraria, paid expert testimony, patent applications/registrations, and grants or other funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
None.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kumar, M., Jindal, M.K. Benchmarks for Designing a Secure Devanagari CAPTCHA. SN COMPUT. SCI. 2, 45 (2021). https://doi.org/10.1007/s42979-020-00445-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-020-00445-z