Publication:
Memory Visualization-Based Malware Detection Technique

Simple item page
dc.contributor.authorShah S.S.H.en_US
dc.contributor.authorJamil N.en_US
dc.contributor.authorKhan A.U.R.en_US
dc.contributor.authorid57878344500en_US
dc.contributor.authorid36682671900en_US
dc.contributor.authorid55602487700en_US
dc.date.accessioned2023-05-29T09:36:23Z
dc.date.available2023-05-29T09:36:23Z
dc.date.issued2022
dc.descriptionComputer vision; Machine learning; Malware; Network security; Sensitive data; Visualization; Wavelet transforms; Advanced persistent threat; Data engineering; De-noising; Denoising filters; Machine-learning; Malware analysis; Malwares; Memory analysis; Polymorphic malware; Wavelets transform; Energy security; computer security; machine learning; Computer Security; Machine Learningen_US
dc.description.abstractAdvanced Persistent Threat is an attack campaign in which an intruder or team of intruders establishes a long-term presence on a network to mine sensitive data, which becomes more dangerous when combined with polymorphic malware. This type of malware is not only undetectable, but it also generates multiple variants of the same type of malware in the network and remains in the system�s main memory to avoid detection. Few researchers employ a visualization approach based on a computer�s memory to detect and classify various classes of malware. However, a preprocessing step of denoising the malware images was not considered, which results in an overfitting problem and prevents us from perfectly generalizing a model. In this paper, we introduce a new data engineering approach comprising two main stages: Denoising and Re-Dimensioning. The first aims at reducing or ideally removing the noise in the malware�s memory-based dump files� transformed images. The latter further processes the cleaned image by compressing them to reduce their dimensionality. This is to avoid the overfitting issue and lower the variance, computing cost, and memory utilization. We then built our machine learning model that implements the new data engineering approach and the result shows that the performance metrics of 97.82% for accuracy, 97.66% for precision, 97.25% for recall, and 97.57% for f1-score are obtained. Our new data engineering approach and machine learning model outperform existing solutions by 0.83% accuracy, 0.30% precision, 1.67% recall, and 1.25% f1-score. In addition to that, the computational time and memory usage have also reduced significantly. � 2022 by the authors.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo7611
dc.identifier.doi10.3390/s22197611
dc.identifier.issue19
dc.identifier.scopus2-s2.0-85139811986
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85139811986&doi=10.3390%2fs22197611&partnerID=40&md5=9a1ca29f6242b1ed6bbfcda47ab53340
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26731
dc.identifier.volume22
dc.publisherMDPIen_US
dc.relation.ispartofAll Open Access, Gold, Green
dc.sourceScopus
dc.sourcetitleSensors
dc.titleMemory Visualization-Based Malware Detection Techniqueen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS