Skripsi

DETEKSI SERANGAN FLOODING PADA JARINGAN SMART HOME IPv6 MENGGUNAKAN METODE DECISION TREE

---

The ICMPv6 "Packet TOO BIG" flooding attack presents a significant threat to IPv6 network security, especially when leveraging vulnerabilities in the EUI-64-based automatic address configuration and the Privacy Extension feature. In this type of attack, a single fixed source is used to send a high volume of malicious ICMPv6 packets to multiple destination addresses that share a similar address structure, exploiting both the deterministic nature of the EUI-64 format and weaknesses in packet handling. This can result in excessive network load and reduced performance. To address this, the study employs a simulated dataset to detect such attacks using the Decision Tree algorithm. The model is trained on labeled traffic data consisting of two categories: Benign and Flood. Evaluation results demonstrate an overall accuracy of 92.38%, with the Benign class achieving a precision of 100% and recall of 84.74%, while the Flood class attains a precision of 86.77% and recall of 100%. The F1-Score reflects balanced detection performance, with 91.70% for the Benign class and 92.91% for the Flood class.

---

Availability

Detail Information

Series Title

-

Call Number

T1834312025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 72 hlm.; ilus,; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.620 7

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Keamanan Jaringan
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment