Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing

Deep learning-based malware detectors have been shown to be susceptible to adversarial malware examples, i.e. malware examples that have been deliberately manipulated in order to avoid detection. In light of the vulnerability of deep learning detectors to subtle input file modifications, we propose...

Descripción completa

Detalles Bibliográficos
Autores: Gibert Llauradó, Daniel, Zizzo, Giulio, Le, Quan, Planes Cid, Jordi
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10459.1/465657
Acceso en línea:https://doi.org/10.1109/ACCESS.2024.3392391
https://hdl.handle.net/10459.1/465657
Access Level:acceso abierto
Palabra clave:Adversarial defense
(de)randomized smoothing
Evasion attacks
Machine learning
id ES_ed4e6fb377b412e8a0c3e45f761e7c00
oai_identifier_str oai:recercat.cat:10459.1/465657
network_acronym_str ES
network_name_str España
repository_id_str
spelling Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized SmoothingGibert Llauradó, DanielZizzo, GiulioLe, QuanPlanes Cid, JordiAdversarial defense(de)randomized smoothingEvasion attacksMachine learningDeep learning-based malware detectors have been shown to be susceptible to adversarial malware examples, i.e. malware examples that have been deliberately manipulated in order to avoid detection. In light of the vulnerability of deep learning detectors to subtle input file modifications, we propose a practical defense against adversarial malware examples inspired by (de)randomized smoothing. In this work, we reduce the chances of sampling adversarial content injected by malware authors by selecting correlated subsets of bytes, rather than using Gaussian noise to randomize inputs like in the Computer Vision domain. During training, our chunk-based smoothing scheme trains a base classifier to make classifications on a subset of contiguous bytes or chunk of bytes. At test time, a large number of chunks are then classified by a base classifier and the consensus among these classifications is then reported as the final prediction. We propose two strategies to determine the location of the chunks used for classification: (1) randomly selecting the locations of the chunks and (2) selecting contiguous adjacent chunks. To showcase the effectiveness of our approach, we have trained two classifiers with our chunk-based smoothing schemes on the BODMAS dataset. Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-art evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.This project has received funding from Enterprise Ireland and the European Union’s Horizon 2020 Research and Innovation Programme under the Marie Skłodowska-Curie grant agreement No 847402 and by MCIN/AEI/10.13039/501100011033/FEDER, UE under the project PID2022-139835NB-C22.Institute of Electrical and Electronics Engineers2024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://doi.org/10.1109/ACCESS.2024.3392391https://hdl.handle.net/10459.1/465657reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-139835NB-C22Reproducció del document publicat a https://doi.org/10.1109/ACCESS.2024.3392391IEEE Access, 2024, vol. 12, p. 61152-61162info:eu-repo/grantAgreement/EC/H2020/847402cc-by (c) Daniel Gibert et al., 2024info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/4.0/oai:recercat.cat:10459.1/4656572026-05-29T05:05:01Z
dc.title.none.fl_str_mv Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
title Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
spellingShingle Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
Gibert Llauradó, Daniel
Adversarial defense
(de)randomized smoothing
Evasion attacks
Machine learning
title_short Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
title_full Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
title_fullStr Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
title_full_unstemmed Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
title_sort Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
dc.creator.none.fl_str_mv Gibert Llauradó, Daniel
Zizzo, Giulio
Le, Quan
Planes Cid, Jordi
author Gibert Llauradó, Daniel
author_facet Gibert Llauradó, Daniel
Zizzo, Giulio
Le, Quan
Planes Cid, Jordi
author_role author
author2 Zizzo, Giulio
Le, Quan
Planes Cid, Jordi
author2_role author
author
author
dc.subject.none.fl_str_mv Adversarial defense
(de)randomized smoothing
Evasion attacks
Machine learning
topic Adversarial defense
(de)randomized smoothing
Evasion attacks
Machine learning
description Deep learning-based malware detectors have been shown to be susceptible to adversarial malware examples, i.e. malware examples that have been deliberately manipulated in order to avoid detection. In light of the vulnerability of deep learning detectors to subtle input file modifications, we propose a practical defense against adversarial malware examples inspired by (de)randomized smoothing. In this work, we reduce the chances of sampling adversarial content injected by malware authors by selecting correlated subsets of bytes, rather than using Gaussian noise to randomize inputs like in the Computer Vision domain. During training, our chunk-based smoothing scheme trains a base classifier to make classifications on a subset of contiguous bytes or chunk of bytes. At test time, a large number of chunks are then classified by a base classifier and the consensus among these classifications is then reported as the final prediction. We propose two strategies to determine the location of the chunks used for classification: (1) randomly selecting the locations of the chunks and (2) selecting contiguous adjacent chunks. To showcase the effectiveness of our approach, we have trained two classifiers with our chunk-based smoothing schemes on the BODMAS dataset. Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-art evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.
publishDate 2024
dc.date.none.fl_str_mv 2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://doi.org/10.1109/ACCESS.2024.3392391
https://hdl.handle.net/10459.1/465657
url https://doi.org/10.1109/ACCESS.2024.3392391
https://hdl.handle.net/10459.1/465657
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-139835NB-C22
Reproducció del document publicat a https://doi.org/10.1109/ACCESS.2024.3392391
IEEE Access, 2024, vol. 12, p. 61152-61162
info:eu-repo/grantAgreement/EC/H2020/847402
dc.rights.none.fl_str_mv cc-by (c) Daniel Gibert et al., 2024
info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/4.0/
rights_invalid_str_mv cc-by (c) Daniel Gibert et al., 2024
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423443044204544
score 15,81155

Similares en LA Referencia