LSGAN-AT: enhancing malware detector robustness against adversarial examples

Abstract Adversarial Malware Example (AME)-based adversarial training can effectively enhance the robustness of Machine Learning (ML)-based malware detectors against AME. AME quality is a key factor to the robustness enhancement. Generative Adversarial Network (GAN) is a kind of AME generation metho...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jianhua Wang, Xiaolin Chang, Yixiang Wang, Ricardo J. Rodríguez, Jianan Zhang
Formato:	article
Lenguaje:	EN
Publicado:	SpringerOpen 2021
Materias:	Adversarial malware example Generative adversarial network Machine learning Malware detector Transferability Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/6cd390847dbd4392914b322c5efd1529
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6cd390847dbd4392914b322c5efd1529
record_format	dspace
spelling	oai:doaj.org-article:6cd390847dbd4392914b322c5efd15292021-12-05T12:10:19ZLSGAN-AT: enhancing malware detector robustness against adversarial examples10.1186/s42400-021-00102-92523-3246https://doaj.org/article/6cd390847dbd4392914b322c5efd15292021-12-01T00:00:00Zhttps://doi.org/10.1186/s42400-021-00102-9https://doaj.org/toc/2523-3246Abstract Adversarial Malware Example (AME)-based adversarial training can effectively enhance the robustness of Machine Learning (ML)-based malware detectors against AME. AME quality is a key factor to the robustness enhancement. Generative Adversarial Network (GAN) is a kind of AME generation method, but the existing GAN-based AME generation methods have the issues of inadequate optimization, mode collapse and training instability. In this paper, we propose a novel approach (denote as LSGAN-AT) to enhance ML-based malware detector robustness against Adversarial Examples, which includes LSGAN module and AT module. LSGAN module can generate more effective and smoother AME by utilizing brand-new network structures and Least Square (LS) loss to optimize boundary samples. AT module makes adversarial training using AME generated by LSGAN to generate ML-based Robust Malware Detector (RMD). Extensive experiment results validate the better transferability of AME in terms of attacking 6 ML detectors and the RMD transferability in terms of resisting the MalGAN black-box attack. The results also verify the performance of the generated RMD in the recognition rate of AME.Jianhua WangXiaolin ChangYixiang WangRicardo J. RodríguezJianan ZhangSpringerOpenarticleAdversarial malware exampleGenerative adversarial networkMachine learningMalware detectorTransferabilityComputer engineering. Computer hardwareTK7885-7895Electronic computers. Computer scienceQA75.5-76.95ENCybersecurity, Vol 4, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Adversarial malware example Generative adversarial network Machine learning Malware detector Transferability Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Adversarial malware example Generative adversarial network Machine learning Malware detector Transferability Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95 Jianhua Wang Xiaolin Chang Yixiang Wang Ricardo J. Rodríguez Jianan Zhang LSGAN-AT: enhancing malware detector robustness against adversarial examples
description	Abstract Adversarial Malware Example (AME)-based adversarial training can effectively enhance the robustness of Machine Learning (ML)-based malware detectors against AME. AME quality is a key factor to the robustness enhancement. Generative Adversarial Network (GAN) is a kind of AME generation method, but the existing GAN-based AME generation methods have the issues of inadequate optimization, mode collapse and training instability. In this paper, we propose a novel approach (denote as LSGAN-AT) to enhance ML-based malware detector robustness against Adversarial Examples, which includes LSGAN module and AT module. LSGAN module can generate more effective and smoother AME by utilizing brand-new network structures and Least Square (LS) loss to optimize boundary samples. AT module makes adversarial training using AME generated by LSGAN to generate ML-based Robust Malware Detector (RMD). Extensive experiment results validate the better transferability of AME in terms of attacking 6 ML detectors and the RMD transferability in terms of resisting the MalGAN black-box attack. The results also verify the performance of the generated RMD in the recognition rate of AME.
format	article
author	Jianhua Wang Xiaolin Chang Yixiang Wang Ricardo J. Rodríguez Jianan Zhang
author_facet	Jianhua Wang Xiaolin Chang Yixiang Wang Ricardo J. Rodríguez Jianan Zhang
author_sort	Jianhua Wang
title	LSGAN-AT: enhancing malware detector robustness against adversarial examples
title_short	LSGAN-AT: enhancing malware detector robustness against adversarial examples
title_full	LSGAN-AT: enhancing malware detector robustness against adversarial examples
title_fullStr	LSGAN-AT: enhancing malware detector robustness against adversarial examples
title_full_unstemmed	LSGAN-AT: enhancing malware detector robustness against adversarial examples
title_sort	lsgan-at: enhancing malware detector robustness against adversarial examples
publisher	SpringerOpen
publishDate	2021
url	https://doaj.org/article/6cd390847dbd4392914b322c5efd1529
work_keys_str_mv	AT jianhuawang lsganatenhancingmalwaredetectorrobustnessagainstadversarialexamples AT xiaolinchang lsganatenhancingmalwaredetectorrobustnessagainstadversarialexamples AT yixiangwang lsganatenhancingmalwaredetectorrobustnessagainstadversarialexamples AT ricardojrodriguez lsganatenhancingmalwaredetectorrobustnessagainstadversarialexamples AT jiananzhang lsganatenhancingmalwaredetectorrobustnessagainstadversarialexamples
_version_	1718372197651709952

LSGAN-AT: enhancing malware detector robustness against adversarial examples

Ejemplares similares