Mobile Based Continuous Authentication Using Deep Features

被引：36

作者：

Centeno, Mario Parreno ^{[1
]}

Guan, Yu ^{[1
]}

van Moorsel, Aad ^{[1
]}

机构：

[1] Newcastle Univ, Newcastle Upon Tyne, Tyne & Wear, England

来源：

PROCEEDINGS OF THE 2018 INTERNATIONAL WORKSHOP ON EMBEDDED AND MOBILE DEEP LEARNING (EMDL '18) | 2018年

基金：

英国工程与自然科学研究理事会;

关键词：

Continuous authentication; Motion authentication; Biometrics; Learning latent representations; Siamese CNN;

D O I：

10.1145/3212725.3212732

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Continuous authentication is a promising approach to validate the user's identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the unauthorised use of mobile devices. Several approaches have been proposed in this area but with relatively weak performance results. In this work, we propose an approach which uses a Siamese convolutional neural network to learn the signatures of the motion patterns from users and achieve a competitive verification accuracy up to 97.8%. We also find our algorithm is not very sensitive to sampling frequency and the length of the sequence.

引用

页码：19 / 24

页数：6

共 12 条

[1]

[Anonymous], 2006, CVPR

[2]

Budiu R., 2015, Mobile User Experience : Limitations and Strengths

[3] Learning a similarity metric discriminatively, with application to face verification [J].

Chopra, S ;

Hadsell, R ;

LeCun, Y .

2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :539-546

[4]

Conti Mauro., 2011, Mind how you answer me!: transparently authenticating the user of a smartphone when answering or placing a call, P249, DOI DOI 10.1145/1966913.1966945

[5]

De Luca A., Proceedings of the 2012 AC M annual conference on Human Factors in Computing Systems, ser. CHI '12. New York, NY, USA: ACM, P987, DOI [DOI 10.1145/2208516.2208544, 10.1145/2208516.2208544]

[6]

Feng T, 2012, 2012 IEEE INTERNATIONAL CONFERENCE ON TECHNOLOGIES FOR HOMELAND SECURITY, P451, DOI 10.1109/THS.2012.6459891

[7]

Gudmundson E, 2009, ISSCS 2009: INTERNATIONAL SYMPOSIUM ON SIGNALS, CIRCUITS AND SYSTEMS, VOLS 1 AND 2, PROCEEDINGS,, P9

[8] A Novel Non-Intrusive User Authentication Method based on Touchscreen of Smartphones [J].

Lin, Chien-Cheng ;

Chang, Chin-Chun ;

Liang, Deron .

2013 INTERNATIONAL SYMPOSIUM ON BIOMETRICS AND SECURITY TECHNOLOGIES (ISBAST), 2013, :212-216

[9] Learning Human Identity From Motion Patterns [J].

Neverova, Natalia ;

Wolf, Christian ;

Lacey, Griffin ;

Fridman, Lex ;

Chandra, Deepak ;

Barbello, Brandon ;

Taylor, Graham .

IEEE ACCESS, 2016, 4 :1810-1820

[10] HMOG: New Behavioral Biometric Features for Continuous Authentication of Smartphone Users [J].

Sitova, Zdenka ;

Sedenka, Jaroslav ;

Yang, Qing ;

Peng, Ge ;

Zhou, Gang ;

Gasti, Paolo ;

Balagani, Kiran S. .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2016, 11 (05) :877-892

← 1 2 →