A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification

Kwok Tai Chui; Brij B. Gupta; Varsha Arya; Ritika Bansal; Francesco Colace

doi:10.1145/3647444.3652455

A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification

Kwok Tai Chui, Brij B. Gupta, Varsha Arya, Ritika Bansal, Francesco Colace

Electronic Engineering and Computer Science

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

Abstract

Classifying malware images is important in cybersecurity. The nature of different families and classes of malware images is imbalanced, which leads to a challenging issue of biased classification, where the majority classes dominate the model's performance. Attention is drawn to generative artificial intelligence, in which a generative adversarial network (GAN) is used to synthesize more training samples (particularly in minority classes). A more balanced dataset can reduce biased classification towards the majority class. However, a robust GAN model usually requires high computing power and a lot of epochs. In this paper, we aim to design a lightweight GAN model to enhance the performance of malware image classification in imbalanced datasets. Performance evaluation and analysis show that it enhances the model's accuracy and reduces its training time. Future research directions are also shared.

Original language	English
Title of host publication	Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023
Editors	Dinesh Goyal, Anil Kumar, Dharm Singh, Marcin Paprzycki, Pooja Jain, B.B. Gupta, Uday Pratap Singh
ISBN (Electronic)	9798400709418
DOIs	https://doi.org/10.1145/3647444.3652455
Publication status	Published - 23 Nov 2023
Event	5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023 - Jaipur, India Duration: 14 Dec 2023 → 16 Dec 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023
Country/Territory	India
City	Jaipur
Period	14/12/23 → 16/12/23

Keywords

artificial intelligence
data generation
generative adversarial network
generative artificial intelligence
imbalanced dataset
malware image

Access to Document

10.1145/3647444.3652455

Cite this

Chui, K. T., Gupta, B. B., Arya, V., Bansal, R., & Colace, F. (2023). A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification. In D. Goyal, A. Kumar, D. Singh, M. Paprzycki, P. Jain, B. B. Gupta, & U. P. Singh (Eds.), Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023 Article 151 (ACM International Conference Proceeding Series). https://doi.org/10.1145/3647444.3652455

Chui, Kwok Tai ; Gupta, Brij B. ; Arya, Varsha et al. / A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification. Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023. editor / Dinesh Goyal ; Anil Kumar ; Dharm Singh ; Marcin Paprzycki ; Pooja Jain ; B.B. Gupta ; Uday Pratap Singh. 2023. (ACM International Conference Proceeding Series).

@inproceedings{a86f27461f194d86a10122b7ade98785,

title = "A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification",

abstract = "Classifying malware images is important in cybersecurity. The nature of different families and classes of malware images is imbalanced, which leads to a challenging issue of biased classification, where the majority classes dominate the model's performance. Attention is drawn to generative artificial intelligence, in which a generative adversarial network (GAN) is used to synthesize more training samples (particularly in minority classes). A more balanced dataset can reduce biased classification towards the majority class. However, a robust GAN model usually requires high computing power and a lot of epochs. In this paper, we aim to design a lightweight GAN model to enhance the performance of malware image classification in imbalanced datasets. Performance evaluation and analysis show that it enhances the model's accuracy and reduces its training time. Future research directions are also shared.",

keywords = "artificial intelligence, data generation, generative adversarial network, generative artificial intelligence, imbalanced dataset, malware image",

author = "Chui, {Kwok Tai} and Gupta, {Brij B.} and Varsha Arya and Ritika Bansal and Francesco Colace",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023 ; Conference date: 14-12-2023 Through 16-12-2023",

year = "2023",

month = nov,

day = "23",

doi = "10.1145/3647444.3652455",

language = "English",

series = "ACM International Conference Proceeding Series",

editor = "Dinesh Goyal and Anil Kumar and Dharm Singh and Marcin Paprzycki and Pooja Jain and B.B. Gupta and Singh, {Uday Pratap}",

booktitle = "Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023",

}

Chui, KT, Gupta, BB, Arya, V, Bansal, R & Colace, F 2023, A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification. in D Goyal, A Kumar, D Singh, M Paprzycki, P Jain, BB Gupta & UP Singh (eds), Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023., 151, ACM International Conference Proceeding Series, 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023, Jaipur, India, 14/12/23. https://doi.org/10.1145/3647444.3652455

A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification. / Chui, Kwok Tai; Gupta, Brij B.; Arya, Varsha et al.
Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023. ed. / Dinesh Goyal; Anil Kumar; Dharm Singh; Marcin Paprzycki; Pooja Jain; B.B. Gupta; Uday Pratap Singh. 2023. 151 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification

AU - Chui, Kwok Tai

AU - Gupta, Brij B.

AU - Arya, Varsha

AU - Bansal, Ritika

AU - Colace, Francesco

PY - 2023/11/23

Y1 - 2023/11/23

N2 - Classifying malware images is important in cybersecurity. The nature of different families and classes of malware images is imbalanced, which leads to a challenging issue of biased classification, where the majority classes dominate the model's performance. Attention is drawn to generative artificial intelligence, in which a generative adversarial network (GAN) is used to synthesize more training samples (particularly in minority classes). A more balanced dataset can reduce biased classification towards the majority class. However, a robust GAN model usually requires high computing power and a lot of epochs. In this paper, we aim to design a lightweight GAN model to enhance the performance of malware image classification in imbalanced datasets. Performance evaluation and analysis show that it enhances the model's accuracy and reduces its training time. Future research directions are also shared.

AB - Classifying malware images is important in cybersecurity. The nature of different families and classes of malware images is imbalanced, which leads to a challenging issue of biased classification, where the majority classes dominate the model's performance. Attention is drawn to generative artificial intelligence, in which a generative adversarial network (GAN) is used to synthesize more training samples (particularly in minority classes). A more balanced dataset can reduce biased classification towards the majority class. However, a robust GAN model usually requires high computing power and a lot of epochs. In this paper, we aim to design a lightweight GAN model to enhance the performance of malware image classification in imbalanced datasets. Performance evaluation and analysis show that it enhances the model's accuracy and reduces its training time. Future research directions are also shared.

KW - artificial intelligence

KW - data generation

KW - generative adversarial network

KW - generative artificial intelligence

KW - imbalanced dataset

KW - malware image

UR - http://www.scopus.com/inward/record.url?scp=85194195020&partnerID=8YFLogxK

U2 - 10.1145/3647444.3652455

DO - 10.1145/3647444.3652455

M3 - Conference contribution

AN - SCOPUS:85194195020

T3 - ACM International Conference Proceeding Series

BT - Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

A2 - Goyal, Dinesh

A2 - Kumar, Anil

A2 - Singh, Dharm

A2 - Paprzycki, Marcin

A2 - Jain, Pooja

A2 - Gupta, B.B.

A2 - Singh, Uday Pratap

T2 - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

Y2 - 14 December 2023 through 16 December 2023

ER -

Chui KT, Gupta BB, Arya V, Bansal R, Colace F. A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification. In Goyal D, Kumar A, Singh D, Paprzycki M, Jain P, Gupta BB, Singh UP, editors, Conference Proceeding - 5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023. 2023. 151. (ACM International Conference Proceeding Series). doi: 10.1145/3647444.3652455

A Lightweight Generative Adversarial Network for Imbalanced Malware Image Classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this