PSyDUCK: Training-Free Steganography for Latent Diffusion

TL;DR

PSyDUCK is a training-free, model-agnostic steganography framework for latent diffusion models, enabling high-capacity, secure message embedding in images and videos with improved accuracy and lower detectability.

Contribution

It introduces a novel, training-free approach for generative steganography in latent diffusion models, extending capabilities to video data and surpassing existing pixel-space methods.

Findings

Achieves higher transmission accuracy in image and video steganography.

Demonstrates lower detectability compared to state-of-the-art techniques.

Extends generative steganography to latent-space video diffusion models.

Abstract

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.