Overlapping variants of sequenced tagged captcha (STC): Generation and their comparative analysis

Sophisticated and evolving CAPTCHA breaking algorithms as mentioned in [1, 4, 7] have successfully broken currently employed CAPTCHAs. This has resulted in a continuous requirement for more robust CAPTCHAs. In light of this, STC generation scheme was introduced in [3] to stay secure for a long time. In this paper, we focus on the generation and comparative study of four variations in STC. These variations occur in overlapping of characters and/or Tagged numbers in the STC and further expand the STC concept. Further, we have identified two parameters viz. readability and security in this paper. These parameters have been used to compare and quantitatively analyze these schemes in order to find a suitably balanced one with an optimum combination of both.

[1]  Patrice Y. Simard,et al.  Using Machine Learning to Break Visual Human Interaction Proofs (HIPs) , 2004, NIPS.

[2]  Jeff Yan,et al.  Usability of CAPTCHAs or usability issues in CAPTCHA design , 2008, SOUPS '08.

[3]  Mikko T. Siponen,et al.  Effective Anti-Spam Strategies in Companies: An International Study , 2006, Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06).

[4]  J. Doug Tygar,et al.  Phish and HIPs: Human Interactive Proofs to Detect Phishing Attacks , 2005, HIP.

[5]  Jeff Yan,et al.  A low-cost attack on a Microsoft captcha , 2008, CCS.

[6]  Ashish Jain,et al.  Sequenced Tagged Captcha: Generation and its Analysis , 2009, 2009 IEEE International Advance Computing Conference.

[7]  Jitendra Malik,et al.  Recognizing objects in adversarial clutter: breaking a visual CAPTCHA , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[8]  Jeff Yan,et al.  Breaking Visual CAPTCHAs with Naive Pattern Recognition Algorithms , 2007, Twenty-Third Annual Computer Security Applications Conference (ACSAC 2007).