Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques
The exponential growth of internet usage and communication devices has led to heightened security vulnerabilities, including the proliferation of malware such as viruses, ransomware, trojans, and spyware. These increasingly sophisticated malware variants pose significant challenges in their detectio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ram Arti Publishers
2025-08-01
|
| Series: | International Journal of Mathematical, Engineering and Management Sciences |
| Subjects: | |
| Online Access: | https://www.ijmems.in/cms/storage/app/public/uploads/volumes/44-IJMEMS-24-0652-10-4-913-930-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850145360122478592 |
|---|---|
| author | Krishna Kumar Hardwari Lal Mandoria Rajeev Singh |
| author_facet | Krishna Kumar Hardwari Lal Mandoria Rajeev Singh |
| author_sort | Krishna Kumar |
| collection | DOAJ |
| description | The exponential growth of internet usage and communication devices has led to heightened security vulnerabilities, including the proliferation of malware such as viruses, ransomware, trojans, and spyware. These increasingly sophisticated malware variants pose significant challenges in their detection and classification. The existing visualization-based deep learning approach addresses some of these challenges but often requires extensive computational resources and prolonged training times and is prone to overfitting. This work proposed a transfer learning-based stacked ensemble technique to enhance the efficiency and accuracy of a malware classification model. The six scaled variants of the EfficientNetB0 architecture are selected for their performance on the ImageNet dataset. Their scalability was trained on the Malimg dataset, which comprises 9,339 malware images across 25 categories. Leveraging transfer learning for feature extraction significantly reduced training time and achieved a competitive accuracy of 99.10% within fewer epochs. To further enhance performance, the study employed a stacked ensemble approach by combining the strengths of three high-performing transfer learning models into two ensemble configurations: an average ensemble and a weighted average ensemble. The weighted average ensemble model demonstrated superior performance, achieving a remarkable training accuracy of 99.84% and a validation accuracy of 99.25%. These results underscore the effectiveness of the proposed approach in addressing modern malware classification challenges efficiently. |
| format | Article |
| id | doaj-art-6f51d78f73e346c3bb9b24564e8aaecd |
| institution | OA Journals |
| issn | 2455-7749 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Ram Arti Publishers |
| record_format | Article |
| series | International Journal of Mathematical, Engineering and Management Sciences |
| spelling | doaj-art-6f51d78f73e346c3bb9b24564e8aaecd2025-08-20T02:28:07ZengRam Arti PublishersInternational Journal of Mathematical, Engineering and Management Sciences2455-77492025-08-01104913930https://doi.org/10.33889/IJMEMS.2025.10.4.044Efficient Malware Classification using Transfer Learning and Stacked Ensemble TechniquesKrishna Kumar0Hardwari Lal Mandoria1Rajeev Singh2Department of Information Technology, College of Technology, G. B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.Department of Information Technology, College of Technology, G. B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.Department of Computer Engineering, College of Technology, G. B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India.The exponential growth of internet usage and communication devices has led to heightened security vulnerabilities, including the proliferation of malware such as viruses, ransomware, trojans, and spyware. These increasingly sophisticated malware variants pose significant challenges in their detection and classification. The existing visualization-based deep learning approach addresses some of these challenges but often requires extensive computational resources and prolonged training times and is prone to overfitting. This work proposed a transfer learning-based stacked ensemble technique to enhance the efficiency and accuracy of a malware classification model. The six scaled variants of the EfficientNetB0 architecture are selected for their performance on the ImageNet dataset. Their scalability was trained on the Malimg dataset, which comprises 9,339 malware images across 25 categories. Leveraging transfer learning for feature extraction significantly reduced training time and achieved a competitive accuracy of 99.10% within fewer epochs. To further enhance performance, the study employed a stacked ensemble approach by combining the strengths of three high-performing transfer learning models into two ensemble configurations: an average ensemble and a weighted average ensemble. The weighted average ensemble model demonstrated superior performance, achieving a remarkable training accuracy of 99.84% and a validation accuracy of 99.25%. These results underscore the effectiveness of the proposed approach in addressing modern malware classification challenges efficiently.https://www.ijmems.in/cms/storage/app/public/uploads/volumes/44-IJMEMS-24-0652-10-4-913-930-2025.pdftransfer learningmalware classificationconvolutional neural networkensemble learningcyber security |
| spellingShingle | Krishna Kumar Hardwari Lal Mandoria Rajeev Singh Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques International Journal of Mathematical, Engineering and Management Sciences transfer learning malware classification convolutional neural network ensemble learning cyber security |
| title | Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques |
| title_full | Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques |
| title_fullStr | Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques |
| title_full_unstemmed | Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques |
| title_short | Efficient Malware Classification using Transfer Learning and Stacked Ensemble Techniques |
| title_sort | efficient malware classification using transfer learning and stacked ensemble techniques |
| topic | transfer learning malware classification convolutional neural network ensemble learning cyber security |
| url | https://www.ijmems.in/cms/storage/app/public/uploads/volumes/44-IJMEMS-24-0652-10-4-913-930-2025.pdf |
| work_keys_str_mv | AT krishnakumar efficientmalwareclassificationusingtransferlearningandstackedensembletechniques AT hardwarilalmandoria efficientmalwareclassificationusingtransferlearningandstackedensembletechniques AT rajeevsingh efficientmalwareclassificationusingtransferlearningandstackedensembletechniques |