Continuous Authentication with Cognition-centric Text
Production and Revision Features

D 2014

Continuous Authentication with Cognition-centric Text Production and Revision Features

LOCKLEAR, Hilbert; Sathya GOVINDARAJAN; Zdeňka SITOVÁ; Adam GOODKIND; David Guy BRIZAN et. al.

Basic information

Original name

Continuous Authentication with Cognition-centric Text Production and Revision Features

Authors

LOCKLEAR, Hilbert (840 United States of America); Sathya GOVINDARAJAN (356 India); Zdeňka SITOVÁ (203 Czech Republic, belonging to the institution); Adam GOODKIND (840 United States of America); David Guy BRIZAN (840 United States of America); Andrew ROSENBERG (840 United States of America); Vir V. PHOHA (840 United States of America); Paolo GASTI (380 Italy) and Kiran S. BALAGANI (356 India)

Edition

USA, International Joint Conference on Biometrics (IJCB), 2014, p. 1-8, 8 pp. 2014

Publisher

IEEE

Other information

Language

English

Type of outcome

Proceedings paper

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

is not subject to a state or trade secret

Publication form

electronic version available online

RIV identification code

RIV/00216224:14330/14:00082090

Organization unit

Faculty of Informatics

ISBN

978-1-4799-3584-0

DOI

http://dx.doi.org/10.1109/BTAS.2014.6996227

EID Scopus

2-s2.0-84921735853

Keywords in English

biometrics;continuous authentication

Abstract

In the original language

Most continuous user authentication techniques based on typing behavior rely on the keystroke dynamics or on the linguistic style of the user. However, there is a rich spectrum of cognition-centric behavioral traits that a typist exhibits during different stages of text production (e.g., composition, translation, and revision), which to our knowledge, have not been considered for continuous authentication. We study the continuous authentication performance of 123 behavioral traits extracted from discrete cognitive units called bursts. We performed experiments on typing data collected from 486 volunteer subjects. Our findings include: (1) features from bursts delimited by pause events have significantly higher availability and authentication performance compared to bursts delimited by revision events; (2) bursts with pause durations of at least one second provide the best authentication accuracy and availability; and (3) fusing our features with traditional keystroke dynamics features reduced authentication error rates. We achieved an equal error rate between 13.37 and 4.55 percent for authentication windows as low as 30 seconds to 3.5 minutes.

Cite

LOCKLEAR, Hilbert; Sathya GOVINDARAJAN; Zdeňka SITOVÁ; Adam GOODKIND; David Guy BRIZAN; Andrew ROSENBERG; Vir V. PHOHA; Paolo GASTI and Kiran S. BALAGANI. Continuous Authentication with Cognition-centric Text Production and Revision Features. Online. In International Joint Conference on Biometrics (IJCB), 2014. USA: IEEE, 2014, p. 1-8. ISBN 978-1-4799-3584-0. Available from: https://dx.doi.org/10.1109/BTAS.2014.6996227.

@inproceedings{1196532,
   author = {Locklear, Hilbert and Govindarajan, Sathya and Sitová, Zdeňka and Goodkind, Adam and Brizan, David Guy and Rosenberg, Andrew and Phoha, Vir V. and Gasti, Paolo and Balagani, Kiran S.},
   address = {USA},
   booktitle = {International Joint Conference on Biometrics (IJCB), 2014},
   doi = {http://dx.doi.org/10.1109/BTAS.2014.6996227},
   keywords = {biometrics;continuous authentication},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {USA},
   isbn = {978-1-4799-3584-0},
   pages = {1-8},
   publisher = {IEEE},
   title = {Continuous Authentication with Cognition-centric Text Production and Revision Features},
   year = {2014}
}

TY  - CONF
ID  - 1196532
AU  - Locklear, Hilbert - Govindarajan, Sathya - Sitová, Zdeňka - Goodkind, Adam - Brizan, David Guy - Rosenberg, Andrew - Phoha, Vir V. - Gasti, Paolo - Balagani, Kiran S.
PY  - 2014
TI  - Continuous Authentication with Cognition-centric Text Production and Revision Features
PB  - IEEE
CY  - USA
SN  - 9781479935840
KW  - biometrics;continuous authentication
N2  - Most continuous user authentication techniques based on typing behavior rely on the keystroke dynamics or on the linguistic style of the user. However, there is a rich spectrum of cognition-centric behavioral traits that a typist exhibits during different stages of text production (e.g., composition, translation, and revision), which to our knowledge, have not been considered for continuous authentication. We study the continuous authentication performance of 123 behavioral traits extracted from discrete cognitive units called bursts. We performed experiments on typing data collected from 486 volunteer subjects. Our findings include: (1) features from bursts delimited by pause events have significantly higher availability and authentication performance compared to bursts delimited by revision events; (2) bursts with pause durations of at least one second provide the best authentication accuracy and availability; and (3) fusing our features with traditional keystroke dynamics features reduced authentication error rates. We achieved an equal error rate between 13.37 and 4.55 percent for authentication windows as low as 30 seconds to 3.5 minutes.
ER  -

LOCKLEAR, Hilbert; Sathya GOVINDARAJAN; Zdeňka SITOVÁ; Adam GOODKIND; David Guy BRIZAN; Andrew ROSENBERG; Vir V. PHOHA; Paolo GASTI and Kiran S. BALAGANI. Continuous Authentication with Cognition-centric Text Production and Revision Features. Online. In \textit{International Joint Conference on Biometrics (IJCB), 2014}. USA: IEEE, 2014, p.~1-8. ISBN~978-1-4799-3584-0. Available from: https://dx.doi.org/10.1109/BTAS.2014.6996227.

Přehled o publikaci