Training-Free Coverless Multi-Image Steganography with Access Control

TL;DR

This paper introduces MIDAS, a training-free diffusion-based coverless image steganography framework that enables multi-image hiding with user-specific access control, improving security, quality, and robustness over existing methods.

Contribution

MIDAS is the first training-free, diffusion-based CIS method that incorporates access control via latent-level fusion, enhancing multi-user privacy and security.

Findings

Outperforms existing CIS methods in access control and image quality.

Demonstrates robustness to noise and steganalysis attacks.

Provides scalable and practical multi-user steganography solution.

Abstract

Coverless Image Steganography (CIS) hides information without explicitly modifying a cover image, providing strong imperceptibility and inherent robustness to steganalysis. However, existing CIS methods largely lack robust access control, making it difficult to selectively reveal different hidden contents to different authorized users. Such access control is critical for scalable and privacy-sensitive information hiding in multi-user settings. We propose MIDAS, a training-free diffusion-based CIS framework that enables multi-image hiding with user-specific access control via latent-level fusion. MIDAS introduces a Random Basis mechanism to suppress residual structural information and a Latent Vector Fusion module that reshapes aggregated latents to align with the diffusion process. Experimental results demonstrate that MIDAS consistently outperforms existing training-free CIS baselines in access control functionality, stego image quality and diversity, robustness to noise, and resistance to steganalysis, establishing a practical and scalable approach to access-controlled coverless steganography.