TIPS: context-aware implicit user identification using touch screen in uncontrolled environments

摘要: Due to the dramatical increase in popularity of mobile devices last decade, more sensitive user information is stored and accessed on these everyday. However, most existing technologies for authentication only cover login stage or work restricted controlled environments GUIs post stage. In this work, we present TIPS, a Touch based Identity Protection Service that implicitly unobtrusively authenticates users background by continuously analyzing touch screen gestures context running application. To best our knowledge, first incorporate contextual app improve authentication. We evaluate TIPS over data collected from 23 phone owners deployed it 13 them with 100 guest users. can achieve 90% accuracy real-life naturalistic conditions within small amount computational overhead 6% battery usage.