cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Joseph Dedy Irawan
Contact Email
joseph@lecturer.itn.ac.id
Phone
+62811367463
Journal Mail Official
ijcomit@itn.ac.id
Editorial Address
Malang National Institute of Technology Jl. Raya Karanglo Km. 2 Malang, Indonesia
Location
Kota malang,
Jawa timur
INDONESIA
International Journal of Computer Science and Information Technology
Published by Institut Teknologi Nasional Malang
ISSN : -     EISSN : 30324955     DOI : https://doi.org/10.36040/ijcomit
Core Subject : Science,
Computer Science & IT
IJCOMIT is a journal of Computer Science and Informatics Technology published by the Computer Science Department, Malang National Institute of Technology, Indonesia, this journal aims to accommodate research articles in the field of Computer Science and Informatics which include programming, interfacing, artificial intelligence, computer networks, cloud technology , embedded systems, image processing, databases, e-commerce, decision-making systems, as well as other fields relevant to Information Technology to publish scientific works in a wide audience.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 21 Documents
 1   2   3 
STEGAFLOW : END-TO-END DEEP NEURAL NETWORKS FOR IMAGE DATA HIDING AND STEGANOGRAPHY Muhammad Romadhona Kusuma; Muhammad Naufal Adnansyah Nuryadin; Rahmat Rahmat; Leo Ternado
International Journal of Computer Science and Information Technology Vol. 3 No. 1 (2026): IJCOMIT Vol 3 No 1
Publisher : Computer Science Department, Malang National Institute of Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/ijcomit.v3i1.18022

Abstract

Deep neural networks are highly sensitive to subtle pixel-level variations, a property that is commonly discussed in the context of adversarial learning. Rather than treating this characteristic solely as a vulnerability, this study explores its potential for image data hiding. This paper proposes StegaFlow, an end-to-end deep learning-based framework for image steganography and blind watermarking, in which encoder and decoder networks are jointly optimized to embed binary messages into digital images while preserving visual quality and enabling reliable message recovery. To improve robustness against real-world image degradations, the training process incorporates multiple distortion models, including Gaussian blur, pixel-wise dropout, image cropping, and JPEG compression. Because JPEG compression is inherently non-differentiable, differentiable approximations are introduced during training to enable effective gradient-based optimization. Experimental results evaluate the proposed framework in terms of capacity, secrecy, and robustness, and show that it achieves strong performance under common image distortions. In particular, the framework demonstrates improved robustness to several spatial-domain degradations, while adversarial training contributes to better perceptual quality by reducing visible embedding artifacts. These findings indicate that end-to-end neural optimization provides a flexible and effective approach for robust image data hiding

Page 3 of 3 | Total Record : 21

 1   2   3 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): IJCOMIT Vol 3 No 1 Vol. 2 No. 2 (2025): IJCOMIT Vol 2 No 2 Vol. 2 No. 1 (2025): IJCOMIT Vol 2 No 1 Vol. 1 No. 2 (2024): IJCOMIT Vol 1 No 2 Vol. 1 No. 1 (2024): IJCOMIT Vol 1 No 1