This chapter describes new challenging methods which are related to the usability of the CAPTCHA test. Firstly, a new strategy for the automatic prediction of the response time to solve the CAPTCHA is presented and described. The proposed strategy is based on regression trees for the prediction of the response time given known personal and demographic features of the Internet users: (i) age, (ii) education level, and (iii) Internet experience level. The involved CAPTCHA types are new trends of the CAPTCHA test: (i) game-based CAPTCHA, and (ii) image-based CAPTCHA. The prediction accuracy of the model is evaluated on collected data from a population of Internet users. The obtained results show that the proposed model is promising in predicting the response time to solve the CAPTCHA test. Secondly, the advanced study of the CAPTCHA usability which employs the association rule mining is extended to the new trends of the CAPTCHA test, i.e. the image-based CAPTCHA. Both approaches represent an important step in the CAPTCHA programming for designing new types of CAPTCHA which can be customized to specific classes of Internet users.
New Trends and Challenges in CAPTCHA Programming
Amelio A.
2020-01-01
Abstract
This chapter describes new challenging methods which are related to the usability of the CAPTCHA test. Firstly, a new strategy for the automatic prediction of the response time to solve the CAPTCHA is presented and described. The proposed strategy is based on regression trees for the prediction of the response time given known personal and demographic features of the Internet users: (i) age, (ii) education level, and (iii) Internet experience level. The involved CAPTCHA types are new trends of the CAPTCHA test: (i) game-based CAPTCHA, and (ii) image-based CAPTCHA. The prediction accuracy of the model is evaluated on collected data from a population of Internet users. The obtained results show that the proposed model is promising in predicting the response time to solve the CAPTCHA test. Secondly, the advanced study of the CAPTCHA usability which employs the association rule mining is extended to the new trends of the CAPTCHA test, i.e. the image-based CAPTCHA. Both approaches represent an important step in the CAPTCHA programming for designing new types of CAPTCHA which can be customized to specific classes of Internet users.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
