Text

PENGAMANAN PESAN DENGAN METODE STEGANOGRAFI BERBASIS CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

Image steganography is implemented in order to maintain the confidentiality and security of information so that it is not easily accessed by unauthorized parties and prevent from cyber security incidents. This research aims to build a system that can embed secret image in RGB format into a carrier image in RGB format. This system uses the Convolutional Neural Network (CNN) method by comparing two architectural configurations, such as 16 convolution layers and 4 concatenation function with 30 convolution layers and 5 concatenation function at the CNNEncoder class. The dataset used is CIFAR10 with 5000 training data, 500 testing data and trained as much as 500 epochs. After the comparison is complete, the best architecture is produced by the second network configuration with an average MSE Loss of 0.5, an average PSNR cover image and payload of 41.3 dB and 28.0 dB without compromising the stego image’s quality and integrity of the embedded information.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307001243	T87164	T871642023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T871642023

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xvi, 71 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.754 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Situs Jejaring Sosial

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment