Skripsi

DETEKSI REVERSE TCP METASPLOIT MENGGUNAKAN GRAPH CONVOLUTIONAL NETWORK

---

Penilaian

---

The rapid development of the open-source Android operating system has made it vulnerable to various cyberattacks, including malware that utilizes the reverse TCP technique. This attack allows an attacker to remotely control a victim’s device through a connection initiated by the device itself, making it difficult to detect using conventional security mechanisms. This research aims to detect reverse TCP attacks on Android using the Graph Convolutional Network (GCN) method. The GCN model was built with two and three convolutional layers to compare performance based on learning rates and data split ratios. Evaluation was conducted using Confusion Matrix metrics, including accuracy, precision, recall, and F1- score. The results showed that the GCN model with three layers and a learning rate of 0.010 achieved the best performance with an accuracy of 88%, 100% recall, and stable validation loss, demonstrating the effectiveness of GCN in detecting reverse TCP attacks. This approach proves that graph-based representations can accurately model node and edge relationships in network traffic to identify malicious activities.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507006195	T185458	T1854582025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1854582025

Publisher

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

Collation

xiii, 74 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.840 7

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Sistem Komputer
Deteksi Malware

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment