Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing

Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sakorn Mekruksavanich, Anuchit Jitpattanakul
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	continuous authentication activity pattern mobile sensing deep learning smartphone Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/b466a1a28c74470791d7c3117ed0bc1b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b466a1a28c74470791d7c3117ed0bc1b
record_format	dspace
spelling	oai:doaj.org-article:b466a1a28c74470791d7c3117ed0bc1b2021-11-25T18:57:05ZDeep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing10.3390/s212275191424-8220https://doaj.org/article/b466a1a28c74470791d7c3117ed0bc1b2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7519https://doaj.org/toc/1424-8220Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails, and storing and accessing personal data at any time and from any location. Nowadays, smartphones are used to store a multitude of private and sensitive data including bank account information, personal identifiers, account passwords and credit card information. Many users remain permanently signed in and, as a result, their mobile devices are vulnerable to security and privacy risks through assaults by criminals. Passcodes, PINs, pattern locks, facial verification, and fingerprint scans are all susceptible to various assaults including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To solve these issues, this research introduces a new continuous authentication framework called DeepAuthen, which identifies smartphone users based on their physical activity patterns as measured by the accelerometer, gyroscope, and magnetometer sensors on their smartphone. We conducted a series of tests on user authentication using several deep learning classifiers, including our proposed deep learning network termed DeepConvLSTM on the three benchmark datasets UCI-HAR, WISDM-HARB and HMOG. Results demonstrated that combining various motion sensor data obtained the highest accuracy and energy efficiency ratio (EER) values for binary classification. We also conducted a thorough examination of the continuous authentication outcomes, and the results supported the efficacy of our framework.Sakorn MekruksavanichAnuchit JitpattanakulMDPI AGarticlecontinuous authenticationactivity patternmobile sensingdeep learningsmartphoneChemical technologyTP1-1185ENSensors, Vol 21, Iss 7519, p 7519 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	continuous authentication activity pattern mobile sensing deep learning smartphone Chemical technology TP1-1185
spellingShingle	continuous authentication activity pattern mobile sensing deep learning smartphone Chemical technology TP1-1185 Sakorn Mekruksavanich Anuchit Jitpattanakul Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
description	Smartphones as ubiquitous gadgets are rapidly becoming more intelligent and context-aware as sensing, networking, and processing capabilities advance. These devices provide users with a comprehensive platform to undertake activities such as socializing, communicating, sending and receiving e-mails, and storing and accessing personal data at any time and from any location. Nowadays, smartphones are used to store a multitude of private and sensitive data including bank account information, personal identifiers, account passwords and credit card information. Many users remain permanently signed in and, as a result, their mobile devices are vulnerable to security and privacy risks through assaults by criminals. Passcodes, PINs, pattern locks, facial verification, and fingerprint scans are all susceptible to various assaults including smudge attacks, side-channel attacks, and shoulder-surfing attacks. To solve these issues, this research introduces a new continuous authentication framework called DeepAuthen, which identifies smartphone users based on their physical activity patterns as measured by the accelerometer, gyroscope, and magnetometer sensors on their smartphone. We conducted a series of tests on user authentication using several deep learning classifiers, including our proposed deep learning network termed DeepConvLSTM on the three benchmark datasets UCI-HAR, WISDM-HARB and HMOG. Results demonstrated that combining various motion sensor data obtained the highest accuracy and energy efficiency ratio (EER) values for binary classification. We also conducted a thorough examination of the continuous authentication outcomes, and the results supported the efficacy of our framework.
format	article
author	Sakorn Mekruksavanich Anuchit Jitpattanakul
author_facet	Sakorn Mekruksavanich Anuchit Jitpattanakul
author_sort	Sakorn Mekruksavanich
title	Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
title_short	Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
title_full	Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
title_fullStr	Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
title_full_unstemmed	Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing
title_sort	deep learning approaches for continuous authentication based on activity patterns using mobile sensing
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b466a1a28c74470791d7c3117ed0bc1b
work_keys_str_mv	AT sakornmekruksavanich deeplearningapproachesforcontinuousauthenticationbasedonactivitypatternsusingmobilesensing AT anuchitjitpattanakul deeplearningapproachesforcontinuousauthenticationbasedonactivitypatternsusingmobilesensing
_version_	1718410548058521600

Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing

Ejemplares similares