Comparison of supervised machine learning algorithms for malware detection / Mohd Faris Mohd Fuzi ... [et al.]
Due to the prevalence of security issues and cyberattacks, cybersecurity is crucial in today's environment. Malware has also evolved significantly over the past few years. With the advancement of malware analysis, Machine Learning (ML) is increasingly being used to detect malware. This study�...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UiTM Cawangan Perlis
2023
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/86867/1/86867.pdf https://ir.uitm.edu.my/id/eprint/86867/ https://crinn.conferencehunter.com/index.php/jcrinn |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Due to the prevalence of security issues and cyberattacks, cybersecurity is crucial in today's environment. Malware has also evolved significantly over the past few years. With the advancement of malware analysis, Machine Learning (ML) is increasingly being used to detect malware. This study's major objective is to compare the best-supervised ML algorithms for malware detection based on detection accuracy. This study includes the scripting and development of supervised ML techniques such as Decision Tree (DT), K-Nearest Neighbors (KNN), Naive Bayes, Random Forest, and Neural Networks. This study was solely concerned with the Windows malware dataset. The malware classification was determined by testing and training the supervised ML algorithms using the extracted features from the malware dataset. Then, the percentage of detection accuracy was used to compare the detection performance of all five algorithms. The detection accuracy is calculated using the confusion matrix, which includes the False Positive Rate (FPR), the True Positive Rate (TPR), and the False Negative Rate (FNR). The results indicated that the Decision Tree and Random Forest algorithms provided the best detection accuracy at 96%, followed by the K-NN algorithm at 95%. To improve the detection accuracy for future research, it is suggested that the malware dataset be enhanced using several architectures, such as Linux and Android, and use additional supervised and unsupervised machine learning algorithms. |
|---|