Special Session: Media Forensics - Fake or Real?

Session Organizers: Luisa Verdoliva and Jana Dittmann.

Submissions are due by March 1st March 15st, 2019.

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

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

Attacks to multimedia data integrity and authenticity become more and more sophisticated by the day. Powerful tools are freely available to manipulate existing data or to generate fake data, be they images, video or audio content. This Special Session focuses on recent advances on how to tell apart fake and real media content. The goal is to bring together researchers and practitioners from different areas of media forensics, with the purpose of analyzing emerging media integrity and authenticity attacks and propose new solutions to counter them, with special emphasis on real-world scenarios. Moreover, the session provides the opportunity to meet, exchange research results, and discuss on the most promising new strategies to ensure multimedia data integrity and authenticity. The special session will include oral presentations. Authors are encouraged to use a set of images provided by the organizers (real, fake/manipulated and mixed-real-fake) to test their proposed approaches, see in

http://niessnerlab.org/projects/roessler2018faceforensics.html
https://omen.cs.uni-magdeburg.de/disclaimer/index.php

Now that the session chairs and general chairs have selected the papers to be included in the technical program we are proudly announcing the of accepted submissions:

  • paper #23 "A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for ICAO-Passport-Scaled Images", by Tom Neubert, Christian Kraetzer and Jana Dittmann (Special session #1)
  • paper #66 "Image Forensics from Chroma Subsampling of High-Quality JPEG Images", by Benedikt Lorch and Christian Riess (Special session #1)
  • paper #68 "A Simple and Effective Initialization of CNN for Forensics of Image Processing Operations", by Ivan Castillo Camacho and Kai Wang (Special session #1)
  • paper #69 "Exposing GAN-synthesized Faces Using Landmark Locations", by Xin Yang, Yuezun Li, Honggang Qi and Siwei Lyu (Special session #1)
  • paper #72 "CNN-based Rescaling Factor Estimation" by Chang Liu and Matthias Kirchner (Special session #1)

 

Special Session: ALASKA challenge on steganogriaphy "into the wild".

Session Organizers: Patrick Bas, Quentin Giboulot and Rémi Cogranne.

Submissions are due by March 15th, 2019.

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

Steganography and Steganalysis had undoubtedly been largely improved by the Break Our Steganographic System (BOSS) challenge in 2010/2011.
This International Challenge gave birth to both very large co-occurrence features-set and classification method for such high-dimensional features space.
The BOSS challenge also provided all researchers in Steganograhy and Steganalysis with a reference dataset, the so-called BOSSbase, that helped many of us to compare different method over the same set of images for a meaningful comparison.
However, we believe that it is time to organize such a similar challenge for many reasons: First, because the introduction of Deep Learning based techniques for steganalysis dramatically changed the state-of-the-art ; second because the BOSSbase has been obtained from the very same conversion process from RAW images. While most of the researchers focused on this specific dataset, recent research works show that changing this dataset or the conversion process may dramatically change the ensuing results.

To update the community with a larger dataset of raw images and a more "diverse" conversion process the ALASKA challenge (https://alaska.utt.fr) has been opened in September 2018.
The goal of this special session is to allow all researchers, who were involved in the ALASKA challenge, to share their experience and to contrast the experiences on steganalysis into highly diverse sources of images.
All participants can submit an extended summary (up to 4-5 pages) by March 1st a quick review process will lead us to select the paper are accepted to submit a full-length paer by March 15th. The acceptance will mostly be based on both the obtained results, the score obtained, and the interest of the underlying methodology to address the diversity of images sources in steganalysis.

After a very selective process we can announce the two accepted submissions for the ALASKA steganalysis challenge special session:

  • paper #67 "The ALASKA Steganalysis Challenge: A first step towards Steganalysis "Into The Wild"", by Rémi Cogranne, Quentin Giboulot and Patrick Bas  (Special session #2)
  • paper #71 "Breaking ALASKA: Poly-Chromatic Multi-Class Deep Residual Neural Network Detector for Steganalysis of Arbitrarily Sized Color JPEG Images", by Yassine Yousfi, Jessica Fridrich, Jan Butora and Quentin Giboulot (Special session #2, certainly ironic title, to be updated)

 

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 are going to 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.

For questions relating to the Call for Papers, please feel free to contact us at : ihmmsec@utt.fr.