Shackled Dancing: A Bit-Locked Diffusion Algorithm for Lossless and Controllable Image Steganography

TL;DR

SD$^2$ introduces Shackled Dancing Diffusion, a diffusion-based steganography method that embeds information by locking specific bit positions in the diffusion denoising trajectory. By combining chaotic encryption, pixel scrambling, and LSB bit locking at designated timesteps, the approach achieves lossless data recovery with up to $4$ bpp while preserving high perceptual image quality. Empirical results show strong robustness to cropping, high extraction accuracy, and a large security margin (key space $>2^{139}$) compared to state-of-the-art methods, with applicability to multimodal payloads. The work advances controllable generation for secure visual communication and opens avenues for more structured conditioning and information-theoretic guarantees in diffusion-based steganography.

Abstract

Data steganography aims to conceal information within visual content, yet existing spatial- and frequency-domain approaches suffer from trade-offs between security, capacity, and perceptual quality. Recent advances in generative models, particularly diffusion models, offer new avenues for adaptive image synthesis, but integrating precise information embedding into the generative process remains challenging. We introduce Shackled Dancing Diffusion, or SD$^2$, a plug-and-play generative steganography method that combines bit-position locking with diffusion sampling injection to enable controllable information embedding within the generative trajectory. SD$^2$ leverages the expressive power of diffusion models to synthesize diverse carrier images while maintaining full message recovery with $100\%$ accuracy. Our method achieves a favorable balance between randomness and constraint, enhancing robustness against steganalysis without compromising image fidelity. Extensive experiments show that SD$^2$ substantially outperforms prior methods in security, embedding capacity, and stability. This algorithm offers new insights into controllable generation and opens promising directions for secure visual communication.

Figures (11)

• Figure 1: Process framework diagram of SD2.
• Figure 2: Schematic diagram of diffusion model.
• Figure 3: Schematic diagram of the steganography information injection process.
• Figure 4: Partial steganographic embedding results. (a--e): carriers, (f): hidden image; (g--k): carriers, (l): hidden image; (m--q): carriers, (r): hidden image; (s--w): carriers, (x): hidden image.
• Figure 5: Steganographic images under varying embedding capacities. (a)--(c): 1 bpp; (d)--(f): 2 bpp; (g)--(i): 3 bpp; (j)--(l): 4 bpp.