Date(s) - 4 Nov 2020
1:00 PM - 2:00 PM
This event will be held virtually.
Speaker: Shen Fu, ECpE Graduate Student
Adviser: Daji Qiao
Title: Data Driven User Authentication with Multi-level Behaviors Profiling
Abstract: The restriction of access to software systems is more important than ever. Yet most primary authentication methods are still largely based on passwords, which are vulnerable to various attacks such as phishing scams and keyloggers. In this work, we dive into the study of user behavior at two levels: software level behavior and mouse operation behavior, seeking innovative data-driven user authentication schemes for general software systems. For software level behavior, we propose a generic continuous authentication scheme, which works as an auxiliary layer to provide additional protection against impostors. For mouse operation behavior, we propose a CNN-RNN combined neural network model for mouse behavior based user authentication, which takes raw sequential mouse data as input rather than relies on heuristic feature extraction. The work presented here is intended to provide authentication schemes via other factors beyond passwords and therefore enhance the security of contemporary software systems.
Bio: Shen Fu received his Bachelor degree from Iowa State University. He is currently pursuing the Ph.D. degree in computer engineering with Iowa State University. His current research interests include data-driven security and privacy, biometric user authentication, deep learning models, interpretability and explainability of machine learning, digital image processing, and communication of powerless IoTs.