Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Are Your Training Datasets Yet Relevant? - An Investigation into the Importance of Timeline in Machine Learning-Based Malware Detection
Allix, Kevin; Bissyande, Tegawendé François D Assise; Klein, Jacques et al.
2015In Engineering Secure Software and Systems - 7th International Symposium ESSoS 2015, Milan, Italy, March 4-6, 2015. Proceedings
Peer reviewed
 

Files


Full Text
essos15_preprint.pdf
Author preprint (641.9 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Machine Learning; Malware Detection; Time; Android
Abstract :
[en] In this paper, we consider the relevance of timeline in the construction of datasets, to highlight its impact on the performance of a machine learning-based malware detection scheme. Typically, we show that simply picking a random set of known malware to train a malware detector, as it is done in many assessment scenarios from the literature, yields significantly biased results. In the process of assessing the extent of this impact through various experiments, we were also able to con- firm a number of intuitive assumptions about Android malware. For instance, we discuss the existence of Android malware lineages and how they could impact the performance of malware detection in the wild.
Research center :
ULHPC - University of Luxembourg: High Performance Computing
Disciplines :
Computer science
Author, co-author :
Allix, Kevin ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Bissyande, Tegawendé François D Assise  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Klein, Jacques ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Le Traon, Yves ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
Are Your Training Datasets Yet Relevant? - An Investigation into the Importance of Timeline in Machine Learning-Based Malware Detection
Publication date :
2015
Event name :
7th International Symposium on Engineering Secure Software and Systems, ESSoS'15
Event place :
Milano, Italy
Event date :
from 04-03-2015 to 06-03-2015
Main work title :
Engineering Secure Software and Systems - 7th International Symposium ESSoS 2015, Milan, Italy, March 4-6, 2015. Proceedings
Publisher :
Springer International Publishing
ISBN/EAN :
978-3-319-15617-0
Pages :
51-67
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 09 March 2015

Statistics


Number of views
1005 (35 by Unilu)
Number of downloads
866 (25 by Unilu)

Scopus citations®
 
46
Scopus citations®
without self-citations
37
OpenCitations
 
30
WoS citations
 
7

Bibliography


Similar publications



Contact ORBilu