SmartAuth: A Behavioral Biometric Authentication System based on Machine Learning

SmartAuth: A Behavioral Biometric Authentication System based on Machine Learning

연구 분야: Analysis

학회: ASENS '24: Proceedings of the International Conference on Algorithms, Software Engineering, and Network Security

Smartphone is an essential part of people's lives, which are often used to store highly sensitive and private information. The information leakage will cause vital security risks for smartphone users. User authentication is a key technology to guarantee smartphone security. Compared with traditional password authentication and face authentication, behavioral bio- metric authentication can keep authenticating the user's identity during use and does not require the user's collaboration in the authentication process. This paper proposes a behavioral bio- metric authentication scheme based on machine learning named SmartAuth, which is a mobile application designed to protect private data on the smartphone by combining touchscreen-based authentication and motion-based authentication. The paper de- scribes the design and implementation of SmartAuth on Android, designs three groups of experiments to verify the performance of the software, and discusses the impact of different machine learning algorithms on the performance.