Research map / Image generation / Autoregressive and latent generation
CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
Jiwen Yu, Xuanyu Zhang, Youmin Xu, Jian Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use zero-shot diffusion-based coverless steganography (CRoSS) instead of trained cover-based RIIS | CRoSS · Stego260 PSNR under Gaussian noise sigma=30 | PSNR (dB): 15.85 -> 18.77 | Improved |
| use CRoSS instead of RIIS under JPEG compression | CRoSS · Stego260 PSNR JPEG Q=80 | PSNR (dB): 27.02 -> 23.51 | Hurt |
| use CRoSS instead of HiNet on clean container images | CRoSS · Stego260 clean reveal | PSNR (dB): 42.98 -> 23.79 | Hurt |
| use CRoSS instead of ISN against steganalysis | CRoSS · Stego260 KeNet detection | |Detection Accuracy - 50|: 8.62 -> 2.11 | Improved |
Later papers that compared with this method
4 later accepted papers report CRoSS as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Large-capacity and Receiver Authenticable Generative Image Steganography (ICML 2026 · better on 4 of 6 shared results)
- KIStego: Key-Independent Secure Image Distribution via Bipartite Structural Invariants (ICML 2026 · better on 6 of 6 shared results)
- Training-Free Coverless Multi-Image Steganography with Access Control (ICML 2026 · better on 5 of 5 shared results)
- MDFL: Multi-Domain Diffusion-Driven Feature Learning (AAAI 2024 · better on 1 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HiNet — HiNet: Deep Image Hiding by Invertible Network (ICCV 2021) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Hiding Images in Diffusion Models by Editing Learned Score Functions (CVPR 2025 · similarity 0.90)
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025 · similarity 0.88)
- SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images (ICML 2025 · similarity 0.88)
- MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models (ICML 2025 · similarity 0.87)
- TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors (ICML 2024 · similarity 0.86)
- AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
