Mobı̇l cı̇hazlarda davranışsal bı̇yometrı̇ kullanarak süreklı̇ kı̇mlı̇k doğrulaması

With the rapid development of technology, smartphones and tablets have become essential objects for our daily lives. Besides their actual purpose of use, people have begun to use these devices as their personal assistants. They are used to make monetary transfers, to arrange their meetings and to make personal messaging by users. Additionally, smartphones and tablets provide large internal storage which enables users to store their private information, such as personal photos, contact details, call histories, etc. On the other hand, because of their small sizes, these devices could easily get lost, stolen. Therefore, providing the security and privacy of smartphone users against unauthorized access is a very important and crucial area of research. Current solutions use active authentication methods, such as PINs and patterns, or use physical biometric authentication, such as fingerprint or iris scan. An alternative solution is the use of behavioral biometrics which track and identify user's interaction patterns with the device. There are various studies on this topic in the literature. However, the authors generally focus on using touchscreen-based or sensor-based features for building an authentication model. In this thesis, we investigated the impact of using both touchscreen-based and sensor-based features in an authentication model.