Ensemble feature selection with discriminative and representative properties for malware detection

Xiao Yu Zhang; Shupeng Wang; Lei Zhang; Chunjie Zhang; Changsheng Li

doi:10.1109/INFCOMW.2016.7562161

Ensemble feature selection with discriminative and representative properties for malware detection

Xiao Yu Zhang
, Shupeng Wang^*
, Lei Zhang
, Chunjie Zhang
, Changsheng Li

^*Corresponding author for this work

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

5 Citations (Scopus)

Abstract

Malware data are typically depicted with extremely high-dimensional features, which lays an excessive computational burden on detection methods. For the sake of effectiveness and efficiency, feature selection is an indispensable part for malware detection. In this paper, we propose an ensemble feature selection method with integration of discriminative and representative properties for malware detection. Based on the labeled and unlabeled data, the most discriminative and representative features are selected, respectively. The former extracts the features that are most distinctive with respect to the classes, and the latter focuses on the features that best represent the data. A comprehensive metric is subsequently obtained, which retains the most informative features.

Original language	English
Title of host publication	2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	674-675
Number of pages	2
ISBN (Electronic)	9781467399555
DOIs	https://doi.org/10.1109/INFCOMW.2016.7562161
Publication status	Published - 6 Sept 2016
Externally published	Yes
Event	35th IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016 - San Francisco, United States Duration: 10 Apr 2016 → 14 Apr 2016

Publication series

Name	Proceedings - IEEE INFOCOM
Volume	2016-September
ISSN (Print)	0743-166X

Conference

Conference	35th IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016
Country/Territory	United States
City	San Francisco
Period	10/04/16 → 14/04/16

Keywords

discriminative feature
feature selection
malware detection
matrix optimization
representative feature

Access to Document

10.1109/INFCOMW.2016.7562161

Cite this

Zhang, X. Y., Wang, S., Zhang, L., Zhang, C., & Li, C. (2016). Ensemble feature selection with discriminative and representative properties for malware detection. In 2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016 (pp. 674-675). Article 7562161 (Proceedings - IEEE INFOCOM; Vol. 2016-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INFCOMW.2016.7562161

@inproceedings{3b6e236cc06041b485a17c7752e6c41f,

title = "Ensemble feature selection with discriminative and representative properties for malware detection",

abstract = "Malware data are typically depicted with extremely high-dimensional features, which lays an excessive computational burden on detection methods. For the sake of effectiveness and efficiency, feature selection is an indispensable part for malware detection. In this paper, we propose an ensemble feature selection method with integration of discriminative and representative properties for malware detection. Based on the labeled and unlabeled data, the most discriminative and representative features are selected, respectively. The former extracts the features that are most distinctive with respect to the classes, and the latter focuses on the features that best represent the data. A comprehensive metric is subsequently obtained, which retains the most informative features.",

keywords = "discriminative feature, feature selection, malware detection, matrix optimization, representative feature",

author = "Zhang, \{Xiao Yu\} and Shupeng Wang and Lei Zhang and Chunjie Zhang and Changsheng Li",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 35th IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016 ; Conference date: 10-04-2016 Through 14-04-2016",

year = "2016",

month = sep,

day = "6",

doi = "10.1109/INFCOMW.2016.7562161",

language = "English",

series = "Proceedings - IEEE INFOCOM",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "674--675",

booktitle = "2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016",

address = "United States",

}

Zhang, XY, Wang, S, Zhang, L, Zhang, C & Li, C 2016, Ensemble feature selection with discriminative and representative properties for malware detection. in 2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016., 7562161, Proceedings - IEEE INFOCOM, vol. 2016-September, Institute of Electrical and Electronics Engineers Inc., pp. 674-675, 35th IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016, San Francisco, United States, 10/04/16. https://doi.org/10.1109/INFCOMW.2016.7562161

Ensemble feature selection with discriminative and representative properties for malware detection. / Zhang, Xiao Yu; Wang, Shupeng; Zhang, Lei et al.
2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 674-675 7562161 (Proceedings - IEEE INFOCOM; Vol. 2016-September).

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

TY - GEN

T1 - Ensemble feature selection with discriminative and representative properties for malware detection

AU - Zhang, Xiao Yu

AU - Wang, Shupeng

AU - Zhang, Lei

AU - Zhang, Chunjie

AU - Li, Changsheng

PY - 2016/9/6

Y1 - 2016/9/6

N2 - Malware data are typically depicted with extremely high-dimensional features, which lays an excessive computational burden on detection methods. For the sake of effectiveness and efficiency, feature selection is an indispensable part for malware detection. In this paper, we propose an ensemble feature selection method with integration of discriminative and representative properties for malware detection. Based on the labeled and unlabeled data, the most discriminative and representative features are selected, respectively. The former extracts the features that are most distinctive with respect to the classes, and the latter focuses on the features that best represent the data. A comprehensive metric is subsequently obtained, which retains the most informative features.

AB - Malware data are typically depicted with extremely high-dimensional features, which lays an excessive computational burden on detection methods. For the sake of effectiveness and efficiency, feature selection is an indispensable part for malware detection. In this paper, we propose an ensemble feature selection method with integration of discriminative and representative properties for malware detection. Based on the labeled and unlabeled data, the most discriminative and representative features are selected, respectively. The former extracts the features that are most distinctive with respect to the classes, and the latter focuses on the features that best represent the data. A comprehensive metric is subsequently obtained, which retains the most informative features.

KW - discriminative feature

KW - feature selection

KW - malware detection

KW - matrix optimization

KW - representative feature

UR - https://www.scopus.com/pages/publications/84988908550

U2 - 10.1109/INFCOMW.2016.7562161

DO - 10.1109/INFCOMW.2016.7562161

M3 - Conference contribution

AN - SCOPUS:84988908550

T3 - Proceedings - IEEE INFOCOM

SP - 674

EP - 675

BT - 2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 35th IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016

Y2 - 10 April 2016 through 14 April 2016

ER -

Zhang XY, Wang S, Zhang L, Zhang C, Li C. Ensemble feature selection with discriminative and representative properties for malware detection. In 2016 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 674-675. 7562161. (Proceedings - IEEE INFOCOM). doi: 10.1109/INFCOMW.2016.7562161

Ensemble feature selection with discriminative and representative properties for malware detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this