Type of Publication

Thesis

Date:

9 /

2023

Status

Published

Noise simulation for the improvement of training deep neural networks for printer-proof steganography

Featured in:

MD Thesis

Authors:

Telmo Cunha

Abstract

In the modern era, images have emerged as powerful tools for concealing information, giving rise to innovative methods like watermarking and steganography, with end-to-end steganography solutions emerging in recent years. However, these new methods presented some issues regarding the hidden message and the decreased quality of images. Additionally, the majority steganography and watermarking methods are only applicable to digital images, since printing or any other physical transformation will destroy the hidden data. This dissertation project investigates the efficacy of noise simulation methods and deep learning methods to improve the resistance of steganography to printing. The research develops an end-to-end printer-proof steganography solution, with a particular focus on the development of a noise simulation module capable of overcoming distortions caused by the transmission of the print-scan medium. Through the development, several approaches are employed, from combining several sources of noise present in the physical environment during printing and capture by image sensors to the introduction of data augmentation techniques and Self-Supervising learning to improve and stabilize the resistance of the steganography solution neural network. Through rigorous experimentation, a significantincrease in the robustness of the neural network was obtained by adding noise combinations while maintaining the performance of the neural network. Thereby, through these experiments, it was proven that noise simulation can provide a robust and efficient method to improve printer-proof steganography.

Citation
Telmo Cunha (2023). Noise simulation for the improvement of training deep neural networks for printer-proof steganography. MD Thesis. University of Coimbra, 2023.

Related Content

Content type: Thesis Presentation

Link: here

Upload Date:2024-10-13T13:55

Researcher Coordinator, VIS TEAM Leader
Post-Doc Researcher
Master Student
News: Scientific Events
StampOne presented at the CVPR 2024...
June 18, 2024
No tagged content to show
No tagged content to show

RECENT PUBLICATIONS

Geometric implicit neural representations for signed distance functions

Authors: Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho
Featured in: Special Section on SIBGRAPI 2023 Tutorials

Towards Secure Biometric Solutions: Enhancing Facial Recognition while Protecting User Data

Authors: Jose Silva, Aniana Cruz, Bruno Sousa and Nuno Gonçalves
Featured in: 14th International Conference on Pattern Recognition Applications and Methods (ICPRAM) 2025

StylePuncher: encoding a hidden QR code into images

Authors: Farhad Shadmand, Luiz Schirmer and Nuno Gonçalves
Featured in: 14th International Conference on Pattern Recognition Applications and Methods (ICPRAM) 2025

suggested news

Best Paper Award @ICPRAM 2025
Nuno Gonçalves serves as jury member for PhD...
ACHILLES project launches official Website and Newsletter

RECENT PROJECTS

FACING2 – Face Image Understanding
VISUAL-ID – Unique Visual Identities in Graphics, Images and Faces
UniqueMark

Institute of Systems and Robotics Department of Electrical and Computers Engineering University of Coimbra