DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models

TL;DR

DiffStega introduces a universal, training-free diffusion-based coverless image steganography method that enhances security and versatility by using password-dependent prompts and a Noise Flip technique, outperforming existing approaches.

Contribution

This work presents a novel training-free diffusion-based CIS approach utilizing password-dependent prompts and Noise Flip for improved security and universality.

Findings

Significant improvements in versatility and recovery quality.

Enhanced password sensitivity and security against unauthorized decryption.

Effective performance across various CIS tasks.

Abstract

Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utilized text prompts as keys in CIS through diffusion models. However, this approach faces three challenges: invalidated when private prompt is guessed, crafting public prompts for semantic diversity, and the risk of prompt leakage during frequent transmission. To address these issues, we propose DiffStega, an innovative training-free diffusion-based CIS strategy for universal application. DiffStega uses a password-dependent reference image as an image prompt alongside the text, ensuring that only authorized parties can retrieve the hidden information. Furthermore, we develop Noise Flip technique to further secure the steganography against unauthorized decryption. To comprehensively assess our method across general CIS tasks, we create a dataset comprising various image steganography instances. Experiments indicate substantial improvements in our method over existing ones, particularly in aspects of versatility, password sensitivity, and recovery quality. Codes are available at \url{https://github.com/evtricks/DiffStega}.