Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models

• URL: http://arxiv.org/abs/2608.13597v1
• Date: Fri, 31 Jul 2026 14:21:59 GMT
• Title: Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models
• Abstract summary: Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image.<n>Existing diffusion-based CIS methods can generate natural-looking stego images but preserve substantial visual similarity to the secret image.<n>We propose InvCISD, an invertible diffusion framework that couples the latent representations of the secret and an irrelevant reference image with an invertible network called LIMNet.
• Score: 7.9584033378193135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego. Existing diffusion-based CIS methods can generate natural-looking stego images but preserve substantial visual similarity to the secret image. This resemblance risks exposing structural and semantic cues, giving rise to security vulnerabilities that cannot be evaluated solely via recovery fidelity. Achieving substantial visual dissimilarity between the secret and stego images without compromising stego quality and recovery fidelity remains challenging. To address this issue, we propose InvCISD, an invertible diffusion framework that couples the latent representations of the secret and an irrelevant reference image with an invertible network called LIMNet. We first train LIMNet in diffusion latent space, followed by end-to-end fine-tuning of the entire network, i.e., LIMNet integrated diffusion inversion and generation modules. Experiments demonstrate that the proposed method substantially reduces secret-stego visual similarity, improves stego quality, and retains satisfactory secret reconstruction quality. Our further investigation shows that all evaluated methods are highly detectable by the CIS-oriented steganalysis model, indicating that resistance against targeted steganalysis constitutes a critical direction for future CIS research.

Related papers

• No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion [15.432428509145703]
  Generative image steganography synthesizes stego images directly from secret information to achieve inherent security advantages.<n>Latent Diffusion Models have emerged as a fundamental image steganography framework that modulates secret latent representations with text prompts.<n>We propose a prompt-free diffusion image steganography framework that integrates style semantic priors to control more robust and reliable stego image generation.
  arXiv  Detail & Related papers  (2026-06-30T09:51:34Z)
• Zero-Shot Interpretable Image Steganalysis for Invertible Image Hiding [9.972200722219076]
  We propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting.<n>Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images.
  arXiv  Detail & Related papers  (2026-05-02T08:55:14Z)
• SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy [53.75084833636302]
  We propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection.<n> SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component.<n>For authorized access, SIDeR can be restored to its original form when the correct password is provided.
  arXiv  Detail & Related papers  (2026-02-04T19:30:48Z)
• Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework [23.969793735154393]
  Current paradigms enforce the secret image to maintain the same resolution as the cover image during hiding and revealing.<n>We propose ARDIS, the first Arbitrary Resolution DIS framework, which shifts the paradigm from discrete mapping to reference-guided continuous signal reconstruction.<n> Experimental results demonstrate that ARDIS significantly outperforms state-of-the-art methods in both invisibility and cross-resolution recovery fidelity.
  arXiv  Detail & Related papers  (2026-01-22T08:07:10Z)
• SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Network [71.11351750072936]
  We propose a novel synergistic framework that achieves 25 image hiding through three key innovations.<n>A network architecture coordinates reversible and non-reversible operations to efficiently exploit information redundancy in both secret and cover images.<n>A unified training strategy that coordinates complementary modules to achieve 3.0x higher capacity than existing methods with superior visual quality.
  arXiv  Detail & Related papers  (2025-03-07T03:31:47Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• FIIH: Fully Invertible Image Hiding for Secure and Robust [4.073420582409583]
  This paper proposes a fully invertible image hiding architecture based on invertible neural network. Based on this ingenious architecture, the method can withstand deep learning based image steganalysis. Experiments demonstrate that the FIIH proposed in this paper significantly outperforms other state-of-the-art image hiding methods in hiding a single image.
  arXiv  Detail & Related papers  (2024-07-24T10:53:14Z)
• Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model [61.53213964333474]
  We propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness.
  arXiv  Detail & Related papers  (2023-12-18T15:25:23Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.