Pattern Password Authentication Based on Touching Location
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F15%3A50004177" target="_blank" >RIV/62690094:18450/15:50004177 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007/978-3-319-24834-9_46" target="_blank" >http://link.springer.com/chapter/10.1007/978-3-319-24834-9_46</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-24834-9_46" target="_blank" >10.1007/978-3-319-24834-9_46</a>
Alternative languages
Result language
angličtina
Original language name
Pattern Password Authentication Based on Touching Location
Original language description
Pattern passwords are one of the embedded authentication method of touchscreen devices, however it has some major drawbacks which briefly are identifiability and imitability. The password of the user is noticeable when entering the pattern due to shiningcircles. Therefore, what we put forward in this paper is a novel biometric implementation of a hidden system to pattern password authentication for increasing password security. As opposed to general research concept which extracts touch or keystroke durations, we focused on the touching coordinates calculated the distance of the line between the constant pattern node and the touched place as well as the angle. Using these inputs, we trained the neural network by Gauss-Newton and Levenberg-Marquardt algorithms and conducted the experiments with these trained classifiers.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Intelligent data engineering and automated learning (IDEAL 2015)
ISBN
978-3-319-24833-2
ISSN
0302-9743
e-ISSN
—
Number of pages
9
Pages from-to
395-403
Publisher name
Springer
Place of publication
Berlin
Event location
Wroclaw
Event date
Oct 14, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—