Teknik Pengesanan Botnet P2P Menggunakan Teknik Pemilihan Ciri

  • Mohammad Hairy Kharauddin Kolej Komuniti Masjid Tanah
  • Wan Ahmad Ramzi Wan Yusuf Kolej Komuniti Masjid Tanah
  • Mohd Fitri Ab Rasid Kolej Komuniti Masjid Tanah

Abstract

Computer networks play an important role in modern society today. A wide range of business, communications, utilities, infrastructure, banking and leisure services are now provided by systems that rely on secure and efficient network operations. As network technology evolves rapidly in size and complexity, the necessary action is to understand the nature of the nature of the network to protect users from dangerous security threats. Botnets are identified as one of the most popular threats of their emergence and P2P botnets use P2P technology for file transfer techniques making these botnets difficult to detect and over the past decade researchers have given more focus in developing more efficient and effective botnet detection methods. In this research, supervised machine learning methods have been used and the main focus is on hybrid models using feature selection techniques or ‘feature selection’. The accuracy and detection of botnets can be improved with the use of hybrid models which show an increase in accuracy from 69.89% to 87.82% detection of botnets in hybrid models compared to filter models. This study will help in identifying the characteristics of botnets and identify the characteristics of P2P botnets with the application of feature selection techniques with hybrid models.

Published
2020-12-01
How to Cite
KHARAUDDIN, Mohammad Hairy; WAN YUSUF, Wan Ahmad Ramzi; AB RASID, Mohd Fitri. Teknik Pengesanan Botnet P2P Menggunakan Teknik Pemilihan Ciri. Politeknik & Kolej Komuniti Journal of Life Long Learning, [S.l.], v. 4, n. 1, p. 84-95, dec. 2020. ISSN 2600-7738. Available at: <https://myjms.mohe.gov.my/index.php/PKKJLLL/article/view/11372>. Date accessed: 18 jan. 2022.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.