Continuous Authentication in the Digital Age: An Analysis of Reinforcement Learning and Behavioural Biometrics
Abstract
This thesis focuses on developing a continuous authentication system using behavioral biometrics to recognize users accessing computing devices. Keystroke dynamics captures the user's unique behavioral biometric, and reward-based reinforcement learning concepts are applied to recognize them throughout the session. The study shows that the proposed system offers an additional layer of security to traditional authentication methods, forming a robust continuous authentication system that can be added to static authentication systems.
Feature extraction technique is applied to enhance performance metrics, and the study concludes that behavioral biometrics are effective in identifying each user, with device information contributing significantly. The research has practical implications for the field of cybersecurity, providing real-world scenarios showing the benefits of enhancing the security of user authentication systems. This research contributes significantly to the field of cybersecurity, addressing challenging questions in building secure knowledge-based user authentication systems.