PiSHi: click the images and I tell if you are a human |
| |
Authors: | Maryam Mehrnezhad Abbas Ghaemi Bafghi Ahad Harati Ehsan Toreini |
| |
Affiliation: | 1.School of Computing Science,Newcastle University,Newcastle upon Tyne,UK;2.Computer Department,Ferdowsi University of Mashhad,Mashhad,Iran |
| |
Abstract: | This paper introduces pictorial intelligent system for human identification (PiSHi), an image-based captcha which uses three human cognitive abilities to distinguish humans from machines. The first is the human ability to easily recognise the image’s upright orientation. The second is the human brain’s ability in recognising a picture’s content when it is only partially visible. And the third is the human ability in unconscious decision making when encountering pictorial challenges. This work models such complicated human patterns in problem solving for the first time. In order to extract these behavioural patterns and save them in a pattern database, we have implemented our own captcha and performed a series of experiments. PiSHi’s interface presents the user with a set of distorted pictures and asks her to click on the upright orientation of all the pictures in any preferred order. Next, it captures the user’s interaction patterns, compares them with the ones saved in the pattern database, and grants her a corresponding credit. Based on this credit, the user either passes or fails the test, and participates in updating the picture database. Our experiments indicate that human users can solve our proposed captcha effectively—with an accuracy of 99.44 %. Besides, our proposed system is secure against several types of attacks including random guessing and reverse image search engines. The results offer the possibility of utilising the identified human behavioural models in practical captchas. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|