Special Session: DNN Watermarking

Session Organizers: M. Barni, F.  Pérez-González, B. Tondi.

Submissions are due by February 26th , 2021.

Click here for a PDF version of the Call for Papers for the special session.

Manuscripts can be submitted here (please read the formatting instructions below).


After 15 years of intense activity, research in media watermarking has seen a declining interest due to the relative maturity of the field. In the last few years, though, the new opportunities offered by Deep Learning (DL) technology and the necessity  of protecting the IPR associated to Deep Neural Networks (DNNs) is revitalising the interest in watermarking technology. On one hand, DNN models can be used for traditional media watermarking (and data hiding in general) offering possible advantages due to the superior capabilities of deep networks to analyze the content of media assets and process them even in the absence of precise statistical models. On the other hand, and even more interestingly, watermarking DNN models for ownership verification or to trace the usage of pre-trained models, presents opportunities and challenges that were not present in the case of media watermarking. As a matter of fact, the three basic requirements of any watermarking system, namely, unobtrusiveness, robustness and even payload, assume a different meaning in the DNN case. For this reason, new techniques have been proposed in the last few years, revealing an extremely rich, and somewhat unexpected, variety of interconnections with some of the hottest topics in DL research, including, adversarial examples, DNN backdoors, identification of synthetic media produced by Generative Adversarial Networks (GAN). It is the goal of this SS to present a snapshot of the current research in DNN watermarking, helping researchers to spot the most interesting open issues and opportunities associated to the field, possibly treasuring on the wealth of theoretical and practical insights stemming from traditional media watermarking.
A non-comprehensive list of topics addressed by the Special Session include:
  • DNN-based media watermarking
  • One-bit vs multibit DNN-based watermarking
  • Dynamic DNN watermarking
  • Static DNN watermarking
  • Black-box vs white box DNN watermarking
  • DNN backdoors and watermarking
  • DNN adversarial examples and watermarking
  • Robustness against fine-tuning and network pruning
  • Security of DNN watermarking
  • Informed coding and DNN watermarking 
  • Joint generation and watermarking of synthetic images 

Formatting instructions

Author information: Paper submission for special session use the same procedures and templates
as for the main workshop (which are recalled below) . The papers will be reviewed in the same manner as regular papers.

For this special session as for the main workshop, papers are to be written in English. Short papers must be 4-6 pages long, while full papers must be 10-12 pages long (including bibliography in both cases). Submissions must follow the new ACM conference template (please use sigconf style). Submissions should not use older ACM formats or non-standard formatting, and must be in pdf format. Authors should devote special care that fonts, images, tables and figures comply with common standards and do not generate problems for reviewers. Submissions not meeting the formatting requirements risk rejection without consideration of their merits.

All submissions should be appropriately anonymized. Author names and affiliations should not appear in the paper. The authors should avoid obvious self-references and should appropriately blind them if used. The list of authors cannot be changed after the acceptance decision is made unless approved by the Program Chairs.

Manuscripts can be submitted here.