Skripsi

DETEKSI SERANGAN MAN IN THE MIDDLE (MITM) PADA SMART HOME MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)

---

MITM attacks allow third parties to infiltrate between communicating devices to steal or modify data without being detected, increasing the security risk of smart home networks. This study aims to detect Man in the Middle (MITM) attacks on smart home networks using the Support Vector Machine (SVM) algorithm. The dataset used is COMNETS SMART HOME, which contains MITM attack data based on the ARP Poisoning technique, extracted from .pcap format to .csv using T-Shark. Random oversampling technique is applied to overcome class imbalance in the dataset to improve detection accuracy. The SVM model was tested with linear, polynomial, and Radial Basis Function (RBF) kernels, with a training and testing data ratio of 50:50 to 90:10. The best comparison was obtained at a ratio of 80:20 with a linear kernel, achieving an accuracy of 98.45%, a precision of 98.03%, a recall of 99.36%, and an F1 score of 98.69%. The results show that SVM with a linear kernel is effective in detecting MITM attacks on smart home networks.

---

Availability

Detail Information

Series Title

-

Call Number

T1593632024

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xvi, 107 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Keamanan Jaringan Komputer

Specific Detail Info

006.310 7

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment