DIMDA: Deep Learning and Image-Based Malware Detection for Android

Vikas Sihag; Surya Prakash; Gaurav choudhary; Nicola Dragoni; Ilsun You

doi:10.1007/978-981-19-5037-7_64

DIMDA: Deep Learning and Image-Based Malware Detection for Android

Vikas Sihag^*
, Surya Prakash
, Gaurav choudhary
, Nicola Dragoni
, Ilsun You

^*Kontaktforfatter

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

Abstract

With the widespread adoption of handheld smartphones, the number of malware targeting them has grown dramatically. Because of the widespread use of cell phones, the quantity of malware has grown dramatically. Because of their ubiquity, android smartphones are the most sought-after targets among smart gadgets. We provide an unique image-based deep learning system for android malware detection in this article. The suggested system predicts if an application is malicious or genuine based on network traffic represented in picture format. The proposed method is tested against 13,533 applications from various banking, gambling, and utilities industries. Our technique is effective, with an accuracy of 98.44% and a recall of 98.30%. It also outperformed conventional machine learning methods.

Originalsprog	Engelsk
Titel	Futuristic Trends in Networks and Computing Technologies : Select Proceedings of 4th International Conference on FTNCT 2021
Redaktører	Pradeep Kumar Singh, Sławomir T. Wierzchoń, Jitender Kumar Chhabra, Sudeep Tanwar
Forlag	Springer
Publikationsdato	2022
Sider	895-906
ISBN (Trykt)	978-981-19-5036-0
DOI	https://doi.org/10.1007/978-981-19-5037-7_64
Status	Udgivet - 2022
Udgivet eksternt	Ja

Navn	Lecture Notes in Electrical Engineering
Vol/bind	936
ISSN	1876-1100

Dokumenter og links

10.1007/978-981-19-5037-7_64

SDU link

Tjek adgangen til materialet i Syddansk Universitetsbiblioteks søgemaskine

Citationsformater

Sihag, V., Prakash, S., choudhary, G., Dragoni, N., & You, I. (2022). DIMDA: Deep Learning and Image-Based Malware Detection for Android. I P. K. Singh, S. T. Wierzchoń, J. K. Chhabra, & S. Tanwar (red.), Futuristic Trends in Networks and Computing Technologies: Select Proceedings of 4th International Conference on FTNCT 2021 (s. 895-906). Springer. https://doi.org/10.1007/978-981-19-5037-7_64

Sihag, Vikas ; Prakash, Surya ; choudhary, Gaurav et al. / DIMDA : Deep Learning and Image-Based Malware Detection for Android. Futuristic Trends in Networks and Computing Technologies: Select Proceedings of 4th International Conference on FTNCT 2021. red. / Pradeep Kumar Singh ; Sławomir T. Wierzchoń ; Jitender Kumar Chhabra ; Sudeep Tanwar. Springer, 2022. s. 895-906 (Lecture Notes in Electrical Engineering, Bind 936).

@inproceedings{9a139b4ad50a47798e2c24f091f047fd,

title = "DIMDA: Deep Learning and Image-Based Malware Detection for Android",

abstract = "With the widespread adoption of handheld smartphones, the number of malware targeting them has grown dramatically. Because of the widespread use of cell phones, the quantity of malware has grown dramatically. Because of their ubiquity, android smartphones are the most sought-after targets among smart gadgets. We provide an unique image-based deep learning system for android malware detection in this article. The suggested system predicts if an application is malicious or genuine based on network traffic represented in picture format. The proposed method is tested against 13,533 applications from various banking, gambling, and utilities industries. Our technique is effective, with an accuracy of 98.44\% and a recall of 98.30\%. It also outperformed conventional machine learning methods.",

keywords = "Android, Deep learning, Malware analysis, Network traffic",

author = "Vikas Sihag and Surya Prakash and Gaurav choudhary and Nicola Dragoni and Ilsun You",

year = "2022",

doi = "10.1007/978-981-19-5037-7\_64",

language = "English",

isbn = "978-981-19-5036-0",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "895--906",

editor = "Singh, \{Pradeep Kumar\} and Wierzcho{\'n}, \{S{\l}awomir T.\} and Chhabra, \{Jitender Kumar\} and Sudeep Tanwar",

booktitle = "Futuristic Trends in Networks and Computing Technologies",

address = "Germany",

}

Sihag, V, Prakash, S, choudhary, G, Dragoni, N & You, I 2022, DIMDA: Deep Learning and Image-Based Malware Detection for Android. i PK Singh, ST Wierzchoń, JK Chhabra & S Tanwar (red), Futuristic Trends in Networks and Computing Technologies: Select Proceedings of 4th International Conference on FTNCT 2021. Springer, Lecture Notes in Electrical Engineering, bind 936, s. 895-906. https://doi.org/10.1007/978-981-19-5037-7_64

DIMDA: Deep Learning and Image-Based Malware Detection for Android. / Sihag, Vikas; Prakash, Surya; choudhary, Gaurav et al.
Futuristic Trends in Networks and Computing Technologies: Select Proceedings of 4th International Conference on FTNCT 2021. red. / Pradeep Kumar Singh; Sławomir T. Wierzchoń; Jitender Kumar Chhabra; Sudeep Tanwar. Springer, 2022. s. 895-906 (Lecture Notes in Electrical Engineering, Bind 936).

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - DIMDA

T2 - Deep Learning and Image-Based Malware Detection for Android

AU - Sihag, Vikas

AU - Prakash, Surya

AU - choudhary, Gaurav

AU - Dragoni, Nicola

AU - You, Ilsun

PY - 2022

Y1 - 2022

N2 - With the widespread adoption of handheld smartphones, the number of malware targeting them has grown dramatically. Because of the widespread use of cell phones, the quantity of malware has grown dramatically. Because of their ubiquity, android smartphones are the most sought-after targets among smart gadgets. We provide an unique image-based deep learning system for android malware detection in this article. The suggested system predicts if an application is malicious or genuine based on network traffic represented in picture format. The proposed method is tested against 13,533 applications from various banking, gambling, and utilities industries. Our technique is effective, with an accuracy of 98.44% and a recall of 98.30%. It also outperformed conventional machine learning methods.

AB - With the widespread adoption of handheld smartphones, the number of malware targeting them has grown dramatically. Because of the widespread use of cell phones, the quantity of malware has grown dramatically. Because of their ubiquity, android smartphones are the most sought-after targets among smart gadgets. We provide an unique image-based deep learning system for android malware detection in this article. The suggested system predicts if an application is malicious or genuine based on network traffic represented in picture format. The proposed method is tested against 13,533 applications from various banking, gambling, and utilities industries. Our technique is effective, with an accuracy of 98.44% and a recall of 98.30%. It also outperformed conventional machine learning methods.

KW - Android

KW - Deep learning

KW - Malware analysis

KW - Network traffic

U2 - 10.1007/978-981-19-5037-7_64

DO - 10.1007/978-981-19-5037-7_64

M3 - Article in proceedings

SN - 978-981-19-5036-0

T3 - Lecture Notes in Electrical Engineering

SP - 895

EP - 906

BT - Futuristic Trends in Networks and Computing Technologies

A2 - Singh, Pradeep Kumar

A2 - Wierzchoń, Sławomir T.

A2 - Chhabra, Jitender Kumar

A2 - Tanwar, Sudeep

PB - Springer

ER -

Sihag V, Prakash S, choudhary G, Dragoni N, You I. DIMDA: Deep Learning and Image-Based Malware Detection for Android. I Singh PK, Wierzchoń ST, Chhabra JK, Tanwar S, red., Futuristic Trends in Networks and Computing Technologies: Select Proceedings of 4th International Conference on FTNCT 2021. Springer. 2022. s. 895-906. (Lecture Notes in Electrical Engineering, Bind 936). doi: 10.1007/978-981-19-5037-7_64

DIMDA: Deep Learning and Image-Based Malware Detection for Android

Abstract

Dokumenter og links

SDU link

Fingeraftryk

Citationsformater