Reference : Android Malware Detection: Looking beyond Dalvik Bytecode
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Security, Reliability and Trust
http://hdl.handle.net/10993/48892
Android Malware Detection: Looking beyond Dalvik Bytecode
English
Sun, Tiezhu mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX >]
Daoudi, Nadia mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX >]
Allix, Kevin mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX >]
Bissyande, Tegawendé François D Assise mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX >]
15-Nov-2021
2021 36th IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW)
Yes
The 4th International Workshop on Advances in Mobile App Analysis
15-11-2021
[en] Android ; Malware detection ; Deep Learning
[en] Machine learning has been widely employed in the literature of malware detection because it is adapted to the need for scalability in vetting large scale samples of Android. Feature engineering has therefore been the key focus for research advances. Recently, a new research direction that builds on the momentum of Deep Learning for computer vision has produced promising results with image representations of Android byte- code. In this work, we postulate that other artifacts such as the binary (native) code and metadata/configuration files could be looked at to build more exhaustive representations of Android apps. We show that binary code and metadata files can also provide relevant information for Android malware detection, i.e., that they can allow to detect Malware that are not detected by models built only on bytecode. Furthermore, we investigate the potential benefits of combining all these artifacts into a unique representation with a strong signal for reasoning about maliciousness.
Fonds National de la Recherche (FNR), Luxembourg ; University of Luxembourg under the HitDroid grant
http://hdl.handle.net/10993/48892

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2021200114.pdfAuthor preprint232.55 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.