Multimodal malware classification using proposed ensemble deep neural network framework

Abstract In the contemporary technological world, fortifying cybersecurity defense against dynamic threat landscapes is imperative. Malware detectors play a critical role in this endeavor, utilizing various techniques such as statistical analysis, static and dynamic analysis, and machine learning (M...

Full description

Saved in:
Bibliographic Details
Main Authors: Sadia Nazim, Muhammad Mansoor Alam, Safdar Rizvi, Jawahir Che Mustapha, Syed Shujaa Hussain, Mazliham Mohd Su’ud
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96203-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850269219283795968
author Sadia Nazim
Muhammad Mansoor Alam
Safdar Rizvi
Jawahir Che Mustapha
Syed Shujaa Hussain
Mazliham Mohd Su’ud
author_facet Sadia Nazim
Muhammad Mansoor Alam
Safdar Rizvi
Jawahir Che Mustapha
Syed Shujaa Hussain
Mazliham Mohd Su’ud
author_sort Sadia Nazim
collection DOAJ
description Abstract In the contemporary technological world, fortifying cybersecurity defense against dynamic threat landscapes is imperative. Malware detectors play a critical role in this endeavor, utilizing various techniques such as statistical analysis, static and dynamic analysis, and machine learning (ML) to compare signatures and identify threats. Deep learning (DL) aids in accurately classifying complex malware features. The cross-domain research in data fusion strives to integrate information from multiple sources to augment reliability and minimize errors in detecting sophisticated cyber threats. This collaborative approach is the least addressed and pivotal for protecting against the advancing environment of modern malware attacks. This study presents a state-of-the-art malware analysis framework that employs a multimodal approach by integrating malware images and numeric features for effective malware classification. The experiments are performed sequentially, encompassing data preprocessing, feature selection using Neighbourhood Component Analysis (NCA), and dataset balancing with Synthetic Minority Over-sampling Technique (SMOTE). Subsequently, the late fusion technique is utilized for multimodal classification by employing Random Under Sampling and Boosting (RUSBoost) and the proposed ensemble deep neural network. The RUSBoost technique involves random undersampling and adaptive boosting to moderate bias toward majority classes while improving minority class (malware) detection. Multimodal Late fusion experimental results (95.36%) of RUSBoost (numeric) and the proposed model (imagery) outperform the standalone prevailing results for imagery (95.02%) and numeric (93.36%) data. The effectiveness of the proposed model is verified through the evaluation metrics such as Recall (86.5%), F1-score (85.0%), and Precision (79.9%). The multimodal late fusion of numeric and visual data makes the model more robust in detecting diverse malware variants. The experimental outcomes demonstrate that multimodal analysis may efficiently increase the identification strength and accuracy, especially when majority vote and bagging are employed for late fusion.
format Article
id doaj-art-a68005f847ff4ba5b5c85687e221a280
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a68005f847ff4ba5b5c85687e221a2802025-08-20T01:53:12ZengNature PortfolioScientific Reports2045-23222025-05-0115112410.1038/s41598-025-96203-3Multimodal malware classification using proposed ensemble deep neural network frameworkSadia Nazim0Muhammad Mansoor Alam1Safdar Rizvi2Jawahir Che Mustapha3Syed Shujaa Hussain4Mazliham Mohd Su’ud5Malaysian Institute of Information Technology, Universiti Kuala LumpurFaculty of Computing, Riphah International UniversityDepartment of Computer Science, Bahria University Karachi CampusMalaysian Institute of Information Technology, Universiti Kuala LumpurDepartment of Computer Science, Sir Syed CASE Institute of TechnologyMultimedia UniversityAbstract In the contemporary technological world, fortifying cybersecurity defense against dynamic threat landscapes is imperative. Malware detectors play a critical role in this endeavor, utilizing various techniques such as statistical analysis, static and dynamic analysis, and machine learning (ML) to compare signatures and identify threats. Deep learning (DL) aids in accurately classifying complex malware features. The cross-domain research in data fusion strives to integrate information from multiple sources to augment reliability and minimize errors in detecting sophisticated cyber threats. This collaborative approach is the least addressed and pivotal for protecting against the advancing environment of modern malware attacks. This study presents a state-of-the-art malware analysis framework that employs a multimodal approach by integrating malware images and numeric features for effective malware classification. The experiments are performed sequentially, encompassing data preprocessing, feature selection using Neighbourhood Component Analysis (NCA), and dataset balancing with Synthetic Minority Over-sampling Technique (SMOTE). Subsequently, the late fusion technique is utilized for multimodal classification by employing Random Under Sampling and Boosting (RUSBoost) and the proposed ensemble deep neural network. The RUSBoost technique involves random undersampling and adaptive boosting to moderate bias toward majority classes while improving minority class (malware) detection. Multimodal Late fusion experimental results (95.36%) of RUSBoost (numeric) and the proposed model (imagery) outperform the standalone prevailing results for imagery (95.02%) and numeric (93.36%) data. The effectiveness of the proposed model is verified through the evaluation metrics such as Recall (86.5%), F1-score (85.0%), and Precision (79.9%). The multimodal late fusion of numeric and visual data makes the model more robust in detecting diverse malware variants. The experimental outcomes demonstrate that multimodal analysis may efficiently increase the identification strength and accuracy, especially when majority vote and bagging are employed for late fusion.https://doi.org/10.1038/s41598-025-96203-3Malware detectionMultimodal analysisDeep learningLate fusionAndroid malwareArtificial intelligence
spellingShingle Sadia Nazim
Muhammad Mansoor Alam
Safdar Rizvi
Jawahir Che Mustapha
Syed Shujaa Hussain
Mazliham Mohd Su’ud
Multimodal malware classification using proposed ensemble deep neural network framework
Scientific Reports
Malware detection
Multimodal analysis
Deep learning
Late fusion
Android malware
Artificial intelligence
title Multimodal malware classification using proposed ensemble deep neural network framework
title_full Multimodal malware classification using proposed ensemble deep neural network framework
title_fullStr Multimodal malware classification using proposed ensemble deep neural network framework
title_full_unstemmed Multimodal malware classification using proposed ensemble deep neural network framework
title_short Multimodal malware classification using proposed ensemble deep neural network framework
title_sort multimodal malware classification using proposed ensemble deep neural network framework
topic Malware detection
Multimodal analysis
Deep learning
Late fusion
Android malware
Artificial intelligence
url https://doi.org/10.1038/s41598-025-96203-3
work_keys_str_mv AT sadianazim multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework
AT muhammadmansooralam multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework
AT safdarrizvi multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework
AT jawahirchemustapha multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework
AT syedshujaahussain multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework
AT mazlihammohdsuud multimodalmalwareclassificationusingproposedensembledeepneuralnetworkframework