Droid-Sec: Deep learning in android malware detection

Zhenlong Yuan; Yongqiang Lu; Zhaoguo Wang; Yibo Xue

doi:10.1145/2619239.2631434

Droid-Sec: Deep learning in android malware detection

Zhenlong Yuan
, Yongqiang Lu
, Zhaoguo Wang
, Yibo Xue

Tsinghua University
Baidu Inc
School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

256 Scopus citations

Abstract

As smartphones and mobile devices are rapidly becoming indispensable for many network users, mobile malware has become a serious threat in the network security and privacy. Especially on the popular Android platform, many malicious apps are hiding in a large number of normal apps, which makes the malware detection more challenging. In this paper, we propose a ML-based method that utilizes more than 200 features extracted from both static analysis and dynamic analysis of Android app for malware detection. The comparison of modeling results demonstrates that the deep learning technique is especially suitable for Android malware detection and can achieve a high level of 96% accuracy with real-world Android application sets.

Original language	English
Title of host publication	Proceedings of the SIGCOMM Chicago 2014 and the Best of the Co-located Workshops
Editors	Konstantina Papagiannaki
Publisher	Association for Computing Machinery
Pages	371-372
Number of pages	2
Volume	44
Edition	4
ISBN (Electronic)	9781450328364
DOIs	https://doi.org/10.1145/2619239.2631434
State	Published - 25 Feb 2015
Externally published	Yes
Event	ACM SIGCOMM 2014 Conference - Chicago, United States Duration: 17 Aug 2014 → 22 Aug 2014

Conference

Conference	ACM SIGCOMM 2014 Conference
Country/Territory	United States
City	Chicago
Period	17/08/14 → 22/08/14

Keywords

Android malware
Deep learning
Detection

Access to Document

10.1145/2619239.2631434

Cite this

@inproceedings{416c77fb19234279b2a3aa5de7fbe0a3,

title = "Droid-Sec: Deep learning in android malware detection",

abstract = "As smartphones and mobile devices are rapidly becoming indispensable for many network users, mobile malware has become a serious threat in the network security and privacy. Especially on the popular Android platform, many malicious apps are hiding in a large number of normal apps, which makes the malware detection more challenging. In this paper, we propose a ML-based method that utilizes more than 200 features extracted from both static analysis and dynamic analysis of Android app for malware detection. The comparison of modeling results demonstrates that the deep learning technique is especially suitable for Android malware detection and can achieve a high level of 96\% accuracy with real-world Android application sets.",

keywords = "Android malware, Deep learning, Detection",

author = "Zhenlong Yuan and Yongqiang Lu and Zhaoguo Wang and Yibo Xue",

year = "2015",

month = feb,

day = "25",

doi = "10.1145/2619239.2631434",

language = "英语",

volume = "44",

pages = "371--372",

editor = "Konstantina Papagiannaki",

booktitle = "Proceedings of the SIGCOMM Chicago 2014 and the Best of the Co-located Workshops",

publisher = "Association for Computing Machinery ",

address = "美国",

edition = "4",

note = "ACM SIGCOMM 2014 Conference ; Conference date: 17-08-2014 Through 22-08-2014",

}

Yuan, Z, Lu, Y, Wang, Z & Xue, Y 2015, Droid-Sec: Deep learning in android malware detection. in K Papagiannaki (ed.), Proceedings of the SIGCOMM Chicago 2014 and the Best of the Co-located Workshops. 4 edn, vol. 44, Association for Computing Machinery , pp. 371-372, ACM SIGCOMM 2014 Conference, Chicago, United States, 17/08/14. https://doi.org/10.1145/2619239.2631434

Droid-Sec: Deep learning in android malware detection. / Yuan, Zhenlong; Lu, Yongqiang; Wang, Zhaoguo et al.
Proceedings of the SIGCOMM Chicago 2014 and the Best of the Co-located Workshops. ed. / Konstantina Papagiannaki. Vol. 44 4. ed. Association for Computing Machinery , 2015. p. 371-372.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Droid-Sec

T2 - ACM SIGCOMM 2014 Conference

AU - Yuan, Zhenlong

AU - Lu, Yongqiang

AU - Wang, Zhaoguo

AU - Xue, Yibo

PY - 2015/2/25

Y1 - 2015/2/25

N2 - As smartphones and mobile devices are rapidly becoming indispensable for many network users, mobile malware has become a serious threat in the network security and privacy. Especially on the popular Android platform, many malicious apps are hiding in a large number of normal apps, which makes the malware detection more challenging. In this paper, we propose a ML-based method that utilizes more than 200 features extracted from both static analysis and dynamic analysis of Android app for malware detection. The comparison of modeling results demonstrates that the deep learning technique is especially suitable for Android malware detection and can achieve a high level of 96% accuracy with real-world Android application sets.

AB - As smartphones and mobile devices are rapidly becoming indispensable for many network users, mobile malware has become a serious threat in the network security and privacy. Especially on the popular Android platform, many malicious apps are hiding in a large number of normal apps, which makes the malware detection more challenging. In this paper, we propose a ML-based method that utilizes more than 200 features extracted from both static analysis and dynamic analysis of Android app for malware detection. The comparison of modeling results demonstrates that the deep learning technique is especially suitable for Android malware detection and can achieve a high level of 96% accuracy with real-world Android application sets.

KW - Android malware

KW - Deep learning

KW - Detection

UR - https://www.scopus.com/pages/publications/84924408055

U2 - 10.1145/2619239.2631434

DO - 10.1145/2619239.2631434

M3 - 会议稿件

AN - SCOPUS:84924408055

VL - 44

SP - 371

EP - 372

BT - Proceedings of the SIGCOMM Chicago 2014 and the Best of the Co-located Workshops

A2 - Papagiannaki, Konstantina

PB - Association for Computing Machinery

Y2 - 17 August 2014 through 22 August 2014

ER -

Droid-Sec: Deep learning in android malware detection

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this