Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Computer & Science Industrial Engineering Journal
Simbolon, Hery Sanjaya
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
DETEKSI SERANGAN MALWARE MENGGUNAKAN METODE SUPPORT VECTOR MACHINE Simbolon, Hery Sanjaya; Maslan, Andi
Computer Science and Industrial Engineering Vol 13 No 2 (2025): Comasie Vol 13 No 2
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i2.10478

Abstract

The rapid development of information technology has increased the potential for threats to system security, one of which is malware attacks. Malware is malicious software that has the ability to disrupt, damage, or steal computer system data without user knowledge. To prevent further damage to the system, malware activity detection is very important. The purpose of this study is to create a classification model that can identify malware attacks based on the behavior of operating system processes when using the Support Vector Machine (SVM) method. The dataset used has 100,000 data entries that have 33 attributes that indicate process activity such as CPU usage, memory, and context shifts. Data is divided into training data and test data, exploratory data analysis (EDA) to understand data characteristics, data preprocessing to clean and standardize attributes, feature selection based on correlation to reduce model complexity, and development and training of a classification model using SVM with a linear kernel. Using a confusion matrix and evaluation metrics such as accuracy, precision, recall, and F1 score, the model is evaluated. Test results show that the developed SVM model performed very well, with an accuracy of 99.57%, a precision of 99.76%, a recall of 99.38%, and an F1 score of 99.57%. This model also distinguished malware processes from normal processes with a very small number of misclassifications. The results indicate that SVM can perform malware detection based on the behavior of system processes quite well. This research can contribute to the development of automated security systems that can detect threats in real time and help strengthen system defenses against cyberattacks.
Co-Authors Maslan, Andi