mlsanityData to 14 Oct 2026

A Brief Survey on Deep Learning Based Data Hiding

arXiv 2103.01607 ↗First posted 2 Mar 2021cs.CR cs.LG cs.MMcited by 9

Not on the map. Why?

Abstract (arXiv)

Data hiding is the art of concealing messages with limited perceptual changes. Recently, deep learning has enriched it from various perspectives with significant progress. In this work, we conduct a brief yet comprehensive review of existing literature for deep learning based data hiding (deep hiding) by first classifying it according to three essential properties (i.e., capacity, security and robustness), and outline three commonly used architectures. Based on this, we summarize specific strategies for different applications of data hiding, including basic hiding, steganography, watermarking and light field messaging. Finally, further insight into deep hiding is provided by incorporating the perspective of adversarial attack.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 24 of its 81 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

24 of 81 references.

References · 24

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  3. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  4. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  5. 2020Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hidingcited by 130
  6. 2020Distortion Agnostic Deep Watermarkingcited by 90
  7. 2019SteganoGAN: High Capacity Image Steganography with GANscited by 72
  8. 2017Generating Steganographic Images via Adversarial Trainingcited by 58
  9. 2018ReDMark: Framework for Residual Diffusion Watermarking on Deep Networkscited by 57
  10. 2014StegExpose - A Tool for Detecting LSB Steganographycited by 25
  11. 2018Invisible Steganography via Generative Adversarial Networkscited by 21
  12. 2019ROMark: A Robust Watermarking System Using Adversarial Trainingcited by 18
12 more
  1. 2021Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspectivecited by 18
  2. 2018StegNet: Mega Image Steganography Capacity with Deep Convolutional Networkcited by 14
  3. 2018WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Imagescited by 8
  4. 2020Robust Spatial-spread Deep Neural Image Watermarkingcited by 6
  5. 2021Multi-Stage Residual Hiding for Image-into-Audio Steganographycited by 6
  6. 2018Generative Steganography by Samplingcited by 5
  7. 2019Hide and Speak: Towards Deep Neural Networks for Speech Steganographycited by 5
  8. 2015Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatchcited by 4
  9. 2020Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approachcited by 4
  10. 2019Steganography using a 3 player gamecited by 3
  11. 2018Detecting Adversarial Examples - A Lesson from Multimedia Forensicscited by 2
  12. 2020DeepMorph: A System for Hiding Bitstrings in Morphable Vector Drawingscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 2; 2024: 2.

9 papers.

  1. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  2. 2021Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganographycited by 24
  3. 2021Watermark Faker: Towards Forgery of Digital Image Watermarkingcited by 8
  4. 2022Hiding Images in Deep Probabilistic Modelscited by 5
  5. 2023A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarkingcited by 3
  6. 2024Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detectioncited by 3
  7. 2022A Screen-Shooting Resilient Document Image Watermarking Scheme using Deep Neural Networkcited by 2
  8. 2023Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelinescited by 1
  9. 2024Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortionscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Deep Learning-based Text-in-Image Watermarking
  2. 2024DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques
  3. 2021A survey of deep neural network watermarking techniques
  4. 2022Deep Fidelity in DNN Watermarking: A Study of Backdoor Watermarking for Classification Models
  5. 2025Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation
  6. 2026Optimizing and Securing the Modern Watermarking Channel for Images
  7. 2023ReMark: Receptive Field based Spatial WaterMark Embedding Optimization using Deep Network
  8. 2021Watermarking Images in Self-Supervised Latent Spaces