Pendeteksian Malware Menggunakan Windows Event Log Dengan Pendekatan Korelasi Event Menggunakan Outlier Detection

Zubaydi, Yusril (2023) Pendeteksian Malware Menggunakan Windows Event Log Dengan Pendekatan Korelasi Event Menggunakan Outlier Detection. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05111940000160-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 July 2026. Download (4MB) | Request a copy

Abstract

Malicious Software (Malware) adalah jenis program yang dibuat untuk menguntungkan pembuatnya. Program ini sering kali digunakan untuk melakukan berbagai serangan seperti mencuri data, melakukan spam, menyerang network, dan masih banyak lagi. Oleh karena itu, malware harus dengan cepat dideteksi agar bisa mengurangi dampak dari malware tersebut. Pada penelitian ini, akan dilakukan pendeteksian malware menggunakan windows event logs dengan pendekatan korelasi event menggunakan outlier detection. Windows Event Logs dipilih karena menyajikan data untuk setiap proses yang dibuat. Dilakukan korelasi event diharapkan dapat memudahkan model dalam proses klasifikasi. Algoritma yang akan digunakan antara lain Isolation Forest, One-Class SVM, dan Local Outlier Factor
=====================================================================================================================================
Malicious Software (Malware) is a type of programthat is created to take advantage from the victim and benefit the creator. This program usually is used for broad range type of attack, such as stealing data, sending spam, penetrating network, and many others. Malware must be quickly detected in order to reduce the impact of the malware. This research will detect malware using Windows Event Logs with event correlation approach using outlier detection. Windows Event Logs was chosen because it present data for every created process. Event correlation is expected to facilitate the model in the classification process. Machine Learning algorithm that will be used are Isolation Forest, One-Class SVM, and Local Outlier Factor

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Deteksi Malware, Unsupervised Machine Learning, Outlier; Detection, Malware Detection, Unsupervised Machine Learning, Outlier Detection.
Subjects:	Q Science > QA Mathematics > QA76.9.A25 Computer security. Digital forensic. Data encryption (Computer science)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Yusril Zubaydi
Date Deposited:	02 Feb 2024 03:01
Last Modified:	02 Feb 2024 03:01
URI:	http://repository.its.ac.id/id/eprint/105922

Actions (login required)

View Item