DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION

Ding Yuxin; Wang Guangbin; Ma Yubin; Ding Haoxuan

doi:10.1109/ICMLC54886.2021.9737271

DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION

Ding Yuxin
, Wang Guangbin
, Ma Yubin
, Ding Haoxuan

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

4 Scopus citations

Abstract

With the rapid development of deep learning technologies, different deep learning models have been applied to detect and classify malware. When applying deep learning models to classify malware families, a major bottleneck is the lack of enough labeled family samples that are required for training deep learning models. The depth model applied to malware needs a huge number of samples for training. In order to solve this issue, we propose a method for generating malware family samples. We use the Grad-CAM algorithm to find the raw data representing malware features. A new sample is created by inserting them into section gaps and new sections in PE files. The experiment results show that adding the generated samples into training dataset can improve the classification accuracy of deep learning models.

Original language	English
Title of host publication	Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665466080
DOIs	https://doi.org/10.1109/ICMLC54886.2021.9737271
State	Published - 2021
Externally published	Yes
Event	20th International Conference on Machine Learning and Cybernetics, ICMLC 2021 - Adelaide, United States Duration: 4 Dec 2021 → 5 Dec 2021

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	2021-December
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	20th International Conference on Machine Learning and Cybernetics, ICMLC 2021
Country/Territory	United States
City	Adelaide
Period	4/12/21 → 5/12/21

Keywords

Data Augmentation
Deep Learning
Feature Extraction

Access to Document

10.1109/ICMLC54886.2021.9737271

Cite this

Yuxin, D., Guangbin, W., Yubin, M., & Haoxuan, D. (2021). DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION. In Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2021-December). IEEE Computer Society. https://doi.org/10.1109/ICMLC54886.2021.9737271

@inproceedings{3278bda17a3b4f97883cd055d330f980,

title = "DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION",

abstract = "With the rapid development of deep learning technologies, different deep learning models have been applied to detect and classify malware. When applying deep learning models to classify malware families, a major bottleneck is the lack of enough labeled family samples that are required for training deep learning models. The depth model applied to malware needs a huge number of samples for training. In order to solve this issue, we propose a method for generating malware family samples. We use the Grad-CAM algorithm to find the raw data representing malware features. A new sample is created by inserting them into section gaps and new sections in PE files. The experiment results show that adding the generated samples into training dataset can improve the classification accuracy of deep learning models.",

keywords = "Data Augmentation, Deep Learning, Feature Extraction",

author = "Ding Yuxin and Wang Guangbin and Ma Yubin and Ding Haoxuan",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 20th International Conference on Machine Learning and Cybernetics, ICMLC 2021 ; Conference date: 04-12-2021 Through 05-12-2021",

year = "2021",

doi = "10.1109/ICMLC54886.2021.9737271",

language = "英语",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021",

address = "美国",

}

Yuxin, D, Guangbin, W, Yubin, M & Haoxuan, D 2021, DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION. in Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021. Proceedings - International Conference on Machine Learning and Cybernetics, vol. 2021-December, IEEE Computer Society, 20th International Conference on Machine Learning and Cybernetics, ICMLC 2021, Adelaide, United States, 4/12/21. https://doi.org/10.1109/ICMLC54886.2021.9737271

DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION. / Yuxin, Ding; Guangbin, Wang; Yubin, Ma et al.
Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021. IEEE Computer Society, 2021. (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2021-December).

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

TY - GEN

T1 - DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION

AU - Yuxin, Ding

AU - Guangbin, Wang

AU - Yubin, Ma

AU - Haoxuan, Ding

PY - 2021

Y1 - 2021

N2 - With the rapid development of deep learning technologies, different deep learning models have been applied to detect and classify malware. When applying deep learning models to classify malware families, a major bottleneck is the lack of enough labeled family samples that are required for training deep learning models. The depth model applied to malware needs a huge number of samples for training. In order to solve this issue, we propose a method for generating malware family samples. We use the Grad-CAM algorithm to find the raw data representing malware features. A new sample is created by inserting them into section gaps and new sections in PE files. The experiment results show that adding the generated samples into training dataset can improve the classification accuracy of deep learning models.

AB - With the rapid development of deep learning technologies, different deep learning models have been applied to detect and classify malware. When applying deep learning models to classify malware families, a major bottleneck is the lack of enough labeled family samples that are required for training deep learning models. The depth model applied to malware needs a huge number of samples for training. In order to solve this issue, we propose a method for generating malware family samples. We use the Grad-CAM algorithm to find the raw data representing malware features. A new sample is created by inserting them into section gaps and new sections in PE files. The experiment results show that adding the generated samples into training dataset can improve the classification accuracy of deep learning models.

KW - Data Augmentation

KW - Deep Learning

KW - Feature Extraction

UR - https://www.scopus.com/pages/publications/85127753732

U2 - 10.1109/ICMLC54886.2021.9737271

DO - 10.1109/ICMLC54886.2021.9737271

M3 - 会议稿件

AN - SCOPUS:85127753732

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

BT - Proceedings of 2021 International Conference on Machine Learning and Cybernetics, ICMLC 2021

PB - IEEE Computer Society

T2 - 20th International Conference on Machine Learning and Cybernetics, ICMLC 2021

Y2 - 4 December 2021 through 5 December 2021

ER -

DATA AUGMENTATION IN TRAINING DEEP LEARNING MODELS FOR MALWARE FAMILY CLASSIFICATION

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this