User authentication based on smartphone application usage patterns through learning classifier systems

Smartphones have become more ubiquitous than ever. People are installing various applications on their smart-phone to fit into their lifestyle. Existing research shows that there are patterns within the ways people access those applications, whether it involves particular locations, particular ranges of time, or many other factors. In this research, through a collaboration with a commercial company, we collected usage data from a popular smartphone application that gives its users access to digital flyers information for shops and supermarkets throughout Japan. Our early experiments found that the pattern information contained inside the data could be used to authenticate users. In this research, we are proposing a behavioral authentication model implementing customized learning classifier systems to search through vast amount of possible patterns to authenticate users of the application. Our early findings for this ongoing research demonstrate that our model can feasibly be a good alternative for additional authentication factor to implicitly authenticate users beyond the initial registration.