B2auth: A contextual fine-grained behavioral biometric authentication framework for real-world deployment

Abstract

Several behavioral biometric authentication frameworks have been proposed to authenticate smartphone users based on the analysis of sensors and services. These authentication frameworks verify the user identity by extracting a set of behavioral traits such as touch, sensors and keystroke dynamics, and use machine learning and deep learning techniques to develop the authentication models. Unfortunately, it is not clear how these frameworks perform in the real world deployment and most of the experiments in the literature have been conducted with cooperative users in a controlled environment. In this paper, we present a novel behavioral biometric authentication framework, called B2auth, designed specifically for smartphone users. The framework leverages raw data collected from touchscreen on smartphone to extract behavioral traits for authentication. A Multilayer Perceptron (MLP) neural network is employed to develop authentication models. Unlike many existing experiments conducted in controlled environments with cooperative users, we focused on real-world deployment scenarios, collecting data from 60 participants using smartphones in an uncontrolled environment. The framework achieves promising results in differentiating the legitimate owner and an attacker across various app contexts, showcasing its potential in practical use cases. By utilizing minimalist data collection and cloud-based model generation, the B2auth framework offers an efficient and effective approach to behavioral biometric authentication for smartphones.