mlsanityData to 14 Oct 2026

CIF: A Constrained Inversion Framework for Reliable Message Extraction in Diffusion-Based Generative Steganography

arXiv 2508.00434 ↗First posted 1 Aug 2025cs.CRcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Generative image steganography aims to conceal secret information in generated images without arousing suspicion. However, in practical scenarios involving high-capacity embedding or lossy transmission, existing methods still suffer from limited extraction accuracy. The main challenge lies in accurately recovering the secret-embedded latent vectors from stego images. To address this issue, we propose CIF, a constrained inversion framework designed to achieve accurate message extraction. Specifically, CIF reduces dynamic structural errors by enforcing linear consistency in the latent space, meanwhile reduces numerical integration errors by adaptively adjusting the integration order according to local trajectory stability. Experimental results show that our method reduces latent reconstruction error by more than 35% and achieves higher message extraction accuracy than existing approaches.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 17 of its 31 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

17 of 31 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025PSyDUCK: Training-Free Steganography for Latent Diffusion31 Jan
  2. 2024Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography7 Sep
  3. 2023Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection30 May
  4. 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography26 May
  5. 2023Generative Steganography Diffusion5 May

Other references · 12

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  9. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  10. 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
  11. 2022Secret-to-Image Reversible Transformation for Generative Steganographycited by 13
  12. 2024Provably Secure Robust Image Steganography via Cross-Modal Error Correctioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
  2. 2026DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent Diffusion
  3. 2023Stable Messenger: Steganography for Message-Concealed Image Generation
  4. 2026Rethinking Security of Diffusion-based Generative Steganography
  5. 2025SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling
  6. 2026Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models
  7. 2025Approximate Gaussian Mapping for Generative Image Steganography
  8. 2024Diffusion-Based Hierarchical Image Steganography