PSyDUCK: Training-Free Steganography for Latent Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahfuz, Aqib, Channing, Georgia, van der Wilk, Mark, Torr, Philip, Pizzati, Fabio, de Witt, Christian Schroeder
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915187221594112
author Mahfuz, Aqib
Channing, Georgia
van der Wilk, Mark
Torr, Philip
Pizzati, Fabio
de Witt, Christian Schroeder
author_facet Mahfuz, Aqib
Channing, Georgia
van der Wilk, Mark
Torr, Philip
Pizzati, Fabio
de Witt, Christian Schroeder
contents Recent advances in generative AI have opened promising avenues for steganography, which can securely protect sensitive information for individuals operating in hostile environments, such as journalists, activists, and whistleblowers. However, existing methods for generative steganography have significant limitations, particularly in scalability and their dependence on retraining diffusion models. We introduce PSyDUCK, a training-free, model-agnostic steganography framework specifically designed for latent diffusion models. PSyDUCK leverages controlled divergence and local mixing within the latent denoising process, enabling high-capacity, secure message embedding without compromising visual fidelity. Our method dynamically adapts embedding strength to balance accuracy and detectability, significantly improving upon existing pixel-space approaches. Crucially, PSyDUCK extends generative steganography to latent-space video diffusion models, surpassing previous methods in both encoding capacity and robustness. Extensive experiments demonstrate PSyDUCK's superiority over state-of-the-art techniques, achieving higher transmission accuracy and lower detectability rates across diverse image and video datasets. By overcoming the key challenges associated with latent diffusion model architectures, PSyDUCK sets a new standard for generative steganography, paving the way for scalable, real-world steganographic applications.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19172
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PSyDUCK: Training-Free Steganography for Latent Diffusion
Mahfuz, Aqib
Channing, Georgia
van der Wilk, Mark
Torr, Philip
Pizzati, Fabio
de Witt, Christian Schroeder
Machine Learning
Cryptography and Security
Recent advances in generative AI have opened promising avenues for steganography, which can securely protect sensitive information for individuals operating in hostile environments, such as journalists, activists, and whistleblowers. However, existing methods for generative steganography have significant limitations, particularly in scalability and their dependence on retraining diffusion models. We introduce PSyDUCK, a training-free, model-agnostic steganography framework specifically designed for latent diffusion models. PSyDUCK leverages controlled divergence and local mixing within the latent denoising process, enabling high-capacity, secure message embedding without compromising visual fidelity. Our method dynamically adapts embedding strength to balance accuracy and detectability, significantly improving upon existing pixel-space approaches. Crucially, PSyDUCK extends generative steganography to latent-space video diffusion models, surpassing previous methods in both encoding capacity and robustness. Extensive experiments demonstrate PSyDUCK's superiority over state-of-the-art techniques, achieving higher transmission accuracy and lower detectability rates across diverse image and video datasets. By overcoming the key challenges associated with latent diffusion model architectures, PSyDUCK sets a new standard for generative steganography, paving the way for scalable, real-world steganographic applications.
title PSyDUCK: Training-Free Steganography for Latent Diffusion
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2501.19172