mlsanityData to 7 Oct 2026

RoSteALS: Robust Steganography using Autoencoder Latent Space

arXiv 2304.03400 ↗First posted 6 Apr 2023cs.CVcited by 54

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Data hiding such as steganography and invisible watermarking has important applications in copyright protection, privacy-preserved communication and content provenance. Existing works often fall short in either preserving image quality, or robustness against perturbations or are too complex to train. We propose RoSteALS, a practical steganography technique leveraging frozen pretrained autoencoders to free the payload embedding from learning the distribution of cover images. RoSteALS has a light-weight secret encoder of just 300k parameters, is easy to train, has perfect secret recovery performance and comparable image quality on three benchmarks. Additionally, RoSteALS can be adapted for novel cover-less steganography applications in which the cover image can be sampled from noise or conditioned on text prompts via a denoising diffusion process. Our model and code are available at urlhttps://github.com/TuBui/RoSteALS.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 25 of its 59 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

25 of 59 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  11. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  12. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
13 more
  1. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  2. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  3. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  4. 2017Searching for Activation Functionscited by 158
  5. 2019Robust Invisible Video Watermarking with Attentioncited by 144
  6. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  7. 2021Watermarking Images in Self-Supervised Latent Spacescited by 90
  8. 2017Steganographic Generative Adversarial Networkscited by 21
  9. 2021OSCAR-Net: Object-centric Scene Graph Attention for Image Attributioncited by 15
  10. 2018StegNet: Mega Image Steganography Capacity with Deep Convolutional Networkcited by 14
  11. 2021VPN: Video Provenance Network for Robust Content Attributioncited by 7
  12. 2018Coverless information hiding based on Generative Modelcited by 3
  13. 2022Image data hiding with multi-scale autoencoder networkcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 16; 2025: 16; 2026: 18.

54 papers.

Sort:

By area:

  1. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
  2. 2024Watermark Anything with Localized Messagescited by 49
  3. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRAcited by 42
  4. 2023WavMark: Watermarking for Audio Generationcited by 41
  5. 2024Self-Improving Diffusion Models with Synthetic Datacited by 34
  6. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  7. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  8. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  9. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  10. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19
  11. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 18
  12. 2024ProMark: Proactive Diffusion Watermarking for Causal Attributioncited by 16
38 more
  1. 2025Watermarking Autoregressive Image Generationcited by 15
  2. 2025Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integritycited by 14
  3. 2024Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensicscited by 12
  4. 2024Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?cited by 10
  5. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 10
  6. 2025On the Difficulty of Constructing a Robust and Publicly-Detectable Watermarkcited by 9
  7. 2023DECORAIT -- DECentralized Opt-in/out Registry for AI Trainingcited by 7
  8. 2025DiffMark: Diffusion-based Robust Watermark Against Deepfakescited by 7
  9. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 6
  10. 2024SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolutioncited by 4
  11. 2025On the Coexistence and Ensembling of Watermarkscited by 3
  12. 2023Stable Messenger: Steganography for Message-Concealed Image Generationcited by 2
  13. 2024SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attackscited by 2
  14. 2024SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Trainingcited by 2
  15. 2026Learning to Watermark in the Latent Space of Generative Modelscited by 2
  16. 2024An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weightingcited by 1
  17. 2025Your Text Encoder Can Be An Object-Level Watermarking Controllercited by 1
  18. 2025STCL:Curriculum learning Strategies for deep learning image steganography modelscited by 1
  19. 2025MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarkscited by 1
  20. 2025AuthenLoRA: Entangling Stylization with Imperceptible Watermarks for Copyright-Secure LoRA Adapterscited by 1
  21. 2026Unifying Watermarking via Dimension-Aware Mappingcited by 1
  22. 2026Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defensescited by 1
  23. 2026Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editingcited by 1
  24. 2026Learning Probabilistic Embeddings for Unsupervised Action Segmentationcited by 1
  25. 2024Neural Cover Selection for Image Steganographycited by 0
  26. 2025MultiNeRF: Multiple Watermark Embedding for Neural Radiance Fieldscited by 0
  27. 2025S2LM: Towards Semantic Steganography via Large Language Modelscited by 0
  28. 2025SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editingcited by 0
  29. 2025Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shufflingcited by 0
  30. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarkingcited by 0
  31. 2026AMIF: Authorizable Medical Image Fusion Model with Built-in Authenticationcited by 0
  32. 2026Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generationcited by 0
  33. 2026DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authenticationcited by 0
  34. 2026Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategycited by 0
  35. 2026RAW: Robust Avatar Watermarking -- Benchmarking and Baselinecited by 0
  36. 2026BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Modelscited by 0
  37. 2026Signpost Watermarking: Joint Optimization for Visual Watermark Coexistencecited by 0
  38. 2026AngelFingerprint: A Traceable, Explainable, and White-Box Stealthy Watermark for Text-Guided Image Editingcited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025PSyDUCK: Training-Free Steganography for Latent Diffusion
  2. 2026No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
  3. 2026Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor
  4. 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
  5. 2025SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling
  6. 2025Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix ↗
  7. 2024Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography
  8. 2025Guidance Watermarking for Diffusion Models