Are Deep Neural Networks good for blind image watermarking? - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Are Deep Neural Networks good for blind image watermarking?

Vedran Vukotić
  • Function : Author
  • PersonId : 8581
  • IdHAL : vvukotic
Vivien Chappelier
  • Function : Author
  • PersonId : 1039627


Image watermarking is usually decomposed into three steps: i) some features are extracted from an image, ii) they are modified to embed the watermark, iii) and they are projected back into the image space while avoiding the creation of visual artefacts. The feature extraction is usually based on a classical image representation given by the Discrete Wavelet Transform or the Discrete Cosine Transform for instance. These transformations need a very accurate syn-chronisation and usually rely on various registration mechanisms for that purpose. This paper investigates a new family of transformation based on Deep Learning networks. Motivations come from the Computer Vision literature which has demonstrated the robustness of these features against light geometric distortions. Also, adversarial sample literature provides means to implement the inverse transform needed in the third step. This paper shows that this approach is feasible as it yields a good quality of the watermarked images and an intrinsic robustness.
Fichier principal
Vignette du fichier
WIFS_2018___Neuralmark-3.pdf (4.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01936750 , version 1 (27-11-2018)


  • HAL Id : hal-01936750 , version 1


Vedran Vukotić, Vivien Chappelier, Teddy Furon. Are Deep Neural Networks good for blind image watermarking?. WIFS 2018 - International Workshop on Information Forensics and Security, Dec 2018, Hong-Kong, China. pp.1-7. ⟨hal-01936750⟩
253 View
1322 Download


Gmail Facebook X LinkedIn More