Laporan Praktek Penelitian Laboratorium Komputasi Berbasis Jaringan Departemen Teknik Informatika dengan Tema: Steganografi Berbasis Varians Lokal Piksel

Salim, Basten Andika (2026) Laporan Praktek Penelitian Laboratorium Komputasi Berbasis Jaringan Departemen Teknik Informatika dengan Tema: Steganografi Berbasis Varians Lokal Piksel. Project Report. [s.n.]. (Unpublished)

Text 5025231132-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (746kB) | Request a copy

Abstract

Keamanan pengiriman data menjadi tantangan penting dengan meningkatnya ancaman siber pada sistem informasi, terutama dalam bidang seperti bidang kesehatan. Steganografi menawarkan solusi untuk permasalahan tersebut dengan menyembunyikan keberadaan data rahasia di dalam gambar medis. Kerja praktik ini merancang dan mengimplementasikan VARStego, metode Reversible Data Hiding yang mengombinasikan kompresi Huffman dengan strategi penyisipan yang adaptif berbasis varians lokal piksel. Varians lokal setiap piksel dihitung untuk menentukan kapasitas penyisipan sesuai kompleksitas tekstur, sementara stego key memastikan cover image dapat direkonstruksi sepenuhnya. Sistem diuji pada 15 gambar medis grayscale dari dataset DICOM Library dan Kaggle dengan payload ASCII dan bitstring berbagai ukuran. Hasil pengujian menunjukkan nilai PSNR maksimum 72.192 dB dan SSIM mendekati sempurna (1.0) pada payload 1 kilobit, serta PSNR 51.858 dB pada payload ASCII terbesar (50 kilobyte), dengan reversibilitas sempurna pada seluruh skenario pengujian.

================================================================================

Data transmission security has become an important challenge amid the rising cyber threats to information systems, particularly in fields such as healthcare. Steganography offers a solution to this problem by concealing the existence of secret data within medical images. This practical work designs and implements VARStego, a Reversible Data Hiding method that combines Huffman compression with an adaptive insertion strategy based on the local variance of pixels. The local variance of each pixel is calculated to determine the insertion capacity according to texture complexity, while the stego key ensures that the cover image can be fully reconstructed. The system was tested on 15 grayscale medical images from the DICOM Library and Kaggle datasets using ASCII payloads and bitstrings of various sizes. The test results show a maximum PSNR value of 72.192 dB and an SSIM close to perfect (1.0) at a payload of 1 kilobit, as well as a PSNR of 51.858 dB at the largest ASCII payload (50 kilobytes), with perfect reversibility across all test scenarios.

Item Type:	Monograph (Project Report)
Uncontrolled Keywords:	Steganografi, Reversible Data Hiding, Keamanan Data
Subjects:	Q Science > QA Mathematics > QA76.9.A25 Computer security. Digital forensic. Data encryption (Computer science) T Technology > T Technology (General) > T57.5 Data Processing T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques. Image analysis--Data processing.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Basten Andika Salim
Date Deposited:	24 Jul 2026 06:38
Last Modified:	24 Jul 2026 06:38
URI:	http://repository.its.ac.id/id/eprint/136782

Actions (login required)

View Item