Continuous Authentication for Smart Phone Users
Most authentication systems (password and biometric feature based) use one-time static authentication methods. Such systems are susceptible to masquerade attacks, where unauthorized users can take over a user’s identity after initial authorization compromising the user's security and privacy. A real time continuous authentication system provides better security control where the user is continuously authenticated based on the user’s behavior after initial authorization. Monitoring more user features have shown to yield more accurate results. For continuous authentication of smart phone users, in this work, we evaluate micro movements, orientation and the grasp of user's hand as a set of behavioral features, which can be easily collected from smart phone sensors like the accelerometer, gyroscope, and magnetometer to continuously authenticate users. We demonstrate the use of Machine Learning to design a continuous authentication system.