An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices
The growing use of computer resources in modern society makes it extremely vulnerable to several cyber-attacks, including unauthorized access to equipment and computer systems’ manipulation or utter breakdown. Malicious attacks in the form of malware cause significant harm to systems with...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10830491/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586862397489152 |
|---|---|
| author | Subir Panja Subhash Mondal Amitava Nag Jyoti Prakash Singh Manob Jyoti Saikia Anup Kumar Barman |
| author_facet | Subir Panja Subhash Mondal Amitava Nag Jyoti Prakash Singh Manob Jyoti Saikia Anup Kumar Barman |
| author_sort | Subir Panja |
| collection | DOAJ |
| description | The growing use of computer resources in modern society makes it extremely vulnerable to several cyber-attacks, including unauthorized access to equipment and computer systems’ manipulation or utter breakdown. Malicious attacks in the form of malware cause significant harm to systems with limited resources. Hence, detecting these attacks and promptly implementing a computationally efficient technique is imperative. Utilizing a machine learning (ML) based model is a superior option for promptly identifying malware. This study develops fourteen machine learning models using a five-fold cross-validation technique on the dataset it obtained for research. We compute the execution time and memory used for each of the fourteen ML model developments, considering both all features and the reduced features after applying the data preprocessing methods. We utilized the Extra Tree classifier (ETC) to identify the top ten significant contributing features based on Gini impurity scores, which led to improved accuracy and reduced processing time. After that, we compared the experimental results and found that the Random Forest (RF) classification model on the reduced features set had a prediction accuracy of 99.39% and ROC-AUC values of 0.99. The ETC model prediction yields comparable results, confirming the viability of the suggested model. The proposed model is very resilient, exhibiting an extremely small standard deviation. It is also highly responsive, with reduced execution time and memory utilization. |
| format | Article |
| id | doaj-art-6987f229d0e34ab88094a911cda292d4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6987f229d0e34ab88094a911cda292d42025-01-25T00:02:51ZengIEEEIEEE Access2169-35362025-01-0113126471266510.1109/ACCESS.2025.352687810830491An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained DevicesSubir Panja0https://orcid.org/0009-0008-3583-1396Subhash Mondal1https://orcid.org/0000-0002-4203-8467Amitava Nag2https://orcid.org/0000-0003-4408-7307Jyoti Prakash Singh3https://orcid.org/0000-0002-3742-7484Manob Jyoti Saikia4https://orcid.org/0000-0001-6656-4333Anup Kumar Barman5https://orcid.org/0000-0002-5697-0431Department of Computer Science and Engineering, Central Institute of Technology Kokrajhar, Kokrajhar, Assam, IndiaDepartment of Computer Science and Engineering, Central Institute of Technology Kokrajhar, Kokrajhar, Assam, IndiaDepartment of Computer Science and Engineering, Central Institute of Technology Kokrajhar, Kokrajhar, Assam, IndiaDepartment of Computer Science and Engineering, National Institute of Technology Patna, Patna, Bihar, IndiaElectrical and Computer Engineering Department, University of Memphis, Memphis, TN, USADepartment of Computer Science and Engineering, Central Institute of Technology Kokrajhar, Kokrajhar, Assam, IndiaThe growing use of computer resources in modern society makes it extremely vulnerable to several cyber-attacks, including unauthorized access to equipment and computer systems’ manipulation or utter breakdown. Malicious attacks in the form of malware cause significant harm to systems with limited resources. Hence, detecting these attacks and promptly implementing a computationally efficient technique is imperative. Utilizing a machine learning (ML) based model is a superior option for promptly identifying malware. This study develops fourteen machine learning models using a five-fold cross-validation technique on the dataset it obtained for research. We compute the execution time and memory used for each of the fourteen ML model developments, considering both all features and the reduced features after applying the data preprocessing methods. We utilized the Extra Tree classifier (ETC) to identify the top ten significant contributing features based on Gini impurity scores, which led to improved accuracy and reduced processing time. After that, we compared the experimental results and found that the Random Forest (RF) classification model on the reduced features set had a prediction accuracy of 99.39% and ROC-AUC values of 0.99. The ETC model prediction yields comparable results, confirming the viability of the suggested model. The proposed model is very resilient, exhibiting an extremely small standard deviation. It is also highly responsive, with reduced execution time and memory utilization.https://ieeexplore.ieee.org/document/10830491/Malware detectionrandom forest classifierfeature selectionextra tree classifierresource-constrained deviceexecution time |
| spellingShingle | Subir Panja Subhash Mondal Amitava Nag Jyoti Prakash Singh Manob Jyoti Saikia Anup Kumar Barman An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices IEEE Access Malware detection random forest classifier feature selection extra tree classifier resource-constrained device execution time |
| title | An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices |
| title_full | An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices |
| title_fullStr | An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices |
| title_full_unstemmed | An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices |
| title_short | An Efficient Malware Detection Approach Based on Machine Learning Feature Influence Techniques for Resource-Constrained Devices |
| title_sort | efficient malware detection approach based on machine learning feature influence techniques for resource constrained devices |
| topic | Malware detection random forest classifier feature selection extra tree classifier resource-constrained device execution time |
| url | https://ieeexplore.ieee.org/document/10830491/ |
| work_keys_str_mv | AT subirpanja anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT subhashmondal anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT amitavanag anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT jyotiprakashsingh anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT manobjyotisaikia anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT anupkumarbarman anefficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT subirpanja efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT subhashmondal efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT amitavanag efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT jyotiprakashsingh efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT manobjyotisaikia efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices AT anupkumarbarman efficientmalwaredetectionapproachbasedonmachinelearningfeatureinfluencetechniquesforresourceconstraineddevices |