PENGAMANAN PESAN DENGAN METODE STEGANOGRAFI BERBASIS CONVOLUTIONAL NEURAL NETWORK

HASMI, ARYA DIFO and Farissi, Al and Arsalan, Osvari (2023) PENGAMANAN PESAN DENGAN METODE STEGANOGRAFI BERBASIS CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181823016.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
Preview	Text RAMA_55201_09021181823016_0215128501_0028068806_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (714kB) | Preview
	Text RAMA_55201_09021181823016_0215128501_0028068806_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (460kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (158kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (534kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (456kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (164kB) | Request a copy
	Text RAMA_55201_09021181823016_0215128501_0028068806_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (33kB) | Request a copy
	Text RAMA_55201_09021181823016_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

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.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Steganografi, Keamanan, Konfigurasi, CNN
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Arya Difo Hasmi
Date Deposited:	20 Jan 2023 03:22
Last Modified:	20 Jan 2023 03:22
URI:	http://repository.unsri.ac.id/id/eprint/87164

Actions (login required)

View Item