DocumentCode :
2354444
Title :
A CAPTCHA with Tips Related to Alphabets Upper or Lower Case
Author :
Wei-Bin Lee ; Che-Wei Fan ; Ho, Kayla ; Chyi-Ren Dow
Author_Institution :
Dept. of Inf. Eng. & Comput. Sci., Feng Chia Univ., Taichung, Taiwan
fYear :
2012
fDate :
12-14 Nov. 2012
Firstpage :
458
Lastpage :
461
Abstract :
Due to the ubiquity of web browsers and the dramatic development of dynamic web pages, web applications become the most popular computing model for providing services over the Internet. Unfortunately, this type of systems is vulnerable to the attacks issued by automated programs. CAPTCHA, a challenge-response test, is the most widely used mechanism to protect web application systems from attacks issued by computer programs. By considering the maintenance cost, most of the CAPTCHA systems employ the text-based challenge in which a string is represented as an image. A user is classified as a human by a text-based CAPTCHA if the user can respond a challenge with the exact string shown in the image. One drawback of a text-based CAPTCHA system is that the string is possibly recognized by a computer program equipped with OCR function. Obfuscating text images can strength the robustness of CAPTCHAs. But, it also degrades the usability of the systems. In this paper, we propose a new text-based CAPTCHA mechanism in which each challenge is associated with a tip providing humans enough information to recognize the alphabets in a highly distorted text image. Therefore, our system provides a balance between the effectiveness and human success rates of text-based CAPTCHAs.
Keywords :
Internet; image classification; image representation; online front-ends; optical character recognition; string matching; text analysis; text detection; CAPTCHA robustness; Internet; OCR function; Web application system protection; Web browsers; alphabets lower case; alphabets upper case; attack vulnerability; automated programs; challenge-response test; dynamic Web pages; highly distorted text image; image representation; maintenance cost; string recognition; string representation; system usability degradation; text-based CAPTCHA system; user classification; Character recognition; Computers; Humans; Image segmentation; Optical character recognition software; Security; Usability; CAPTCHA; OCR; Web application;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Broadband, Wireless Computing, Communication and Applications (BWCCA), 2012 Seventh International Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
978-1-4673-2972-9
Type :
conf
DOI :
10.1109/BWCCA.2012.81
Filename :
6363097
Link To Document :
بازگشت