Gait-Based Implicit Authentication Using Edge Computing and Deep Learning for Mobile Devices

Zhicai Shi,Shuqun Yang,Xiaomei Zhang,Xin Zeng,Chihung Chi

doi:10.3390/s21134592

Abstract

Implicit authentication mechanisms are expected to prevent security and privacy threats for mobile devices using behavior modeling. However, recently, researchers have demonstrated that the performance of behavioral biometrics is insufficiently accurate. Furthermore, the unique characteristics of mobile devices, such as limited storage and energy, make it subject to constrained capacity of data collection and processing. In this paper, we propose an implicit authentication architecture based on edge computing, coined Edge computing-based mobile Device Implicit Authentication (EDIA), which exploits edge-based gait biometric identification using a deep learning model to authenticate users. The gait data captured by a device’s accelerometer and gyroscope sensors is utilized as the input of our optimized model, which consists of a CNN and a LSTM in tandem. Especially, we deal with extracting the features of gait signal in a two-dimensional domain through converting the original signal into an image, and then input it into our network. In addition, to reduce computation overhead of mobile devices, the model for implicit authentication is generated on the cloud server, and the user authentication process also takes place on the edge devices. We evaluate the performance of EDIA under different scenarios where the results show that i) we achieve a true positive rate of 97.77% and also a 2% false positive rate; and ii) EDIA still reaches high accuracy with limited dataset size.

Highlights

Mobile devices, including smartphones and tablets, play important roles in our daily lives
We propose an efficient implicit authentication system named Edge computing-based mobile Device Implicit Authentication (EDIA), which uses the gait biometric traits generated by users and captured by build-in sensors
We propose an edge computing-based implicit authentication architecture, EDIA, which is designed to attain high efficiency and computing resources optimization based on the edge computing paradigm; We develop a hybrid model, based on concatenation of Convolutional Neural Networks (CNN) and LSTM accommodated to the optimized process of gait data from build-in sensors

Summary

Introduction

Mobile devices, including smartphones and tablets, play important roles in our daily lives. With the growth in their use, people increasingly store ample private and sensitive information such as photos and emails on mobile devices. Traditional access control methods employ one-time authentication mechanisms, e.g., passcodes, PINs, face recognition and fingerprints, which is asked when users try to start-up their mobile devices. These authentication mechanisms are easy to crack by guessing, smudge attacks and static photos [4]. Users is required to present these credentials only for initial login. Unauthorized users may illegally access to devices if the authentication system is not constantly on guard against intruders after initial login

Methods

Findings

Discussion

Conclusion