Vous êtes ici : Accueil » Kiosque » Annonce


Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?


9 août 2017

Ph.D position at EURECOM Sophia Antipolis in Image Forensics

Catégorie : Doctorant

Image forensics includes two major challenges:

  • The detection of malicious manipulations;
  • The identification of the sensors.

Even if image forensics is quite a new topic, some commercial products already exist. Nonetheless, several open problems still exist:

  • The automation of analysis modules;
  • The integration of such tools in standards, in particular of source coding; extension to video;
  • The robustness of such tools against advanced attackers, themselves experts in image forensics (i.e. counter-forensics).

In this work, the Ph.D student will mainly focus on the automatic detection of image manipulations, according to the following three axes:

  • Automation
    Currently, tools in image forensics require some manual steps that can be done by trained photo-experts. Automation of such tasks would save time, reduce costs attached to training and facilitate the spread of such tools to larger audiences with some new potential domains of application (e.g. social networks).
  • Robustness
    Currently, tools work under the assumption that image manipulations are performed to fool human perception, with no assumption on the possible existence of digital detectors. In the close future, one can imagine that attacks will be improved so that they are undetectable by both humans and machines.
    We may distinguish between different levels of manipulations:
    1. Basic and global processing like source coding or zoom;
    2. Advanced and local processing like cut & paste operations, inpainting.
  • Video
    The current tools are dealing with still images. Nevertheless, videos are more and more important. Extension of algorithms from images to videos is then a priority.

Prospective applicants are encouraged to read the following reference for more information about the exact topic : Digital image forensics: a booklet for beginners, JA Redi, W Taktak, J.-L. Dugelay, J. Multimedia Tools and Applications 51 (1), 133-162


Education Level / Degree: Computer Engineering or Master Degree (with honors); English is mandatory, French is just a plus.


The application must include:
• I-Short Curriculum Vitae
• III-Names and contacts of two references

Applications should be submitted by e-mail to jean-luc.dugelay@eurecom.fr



EURECOM is a French graduate school and a research center in communication systems based in the international science park of Sophia Antipolis within the new Campus SophiaTech, which brings together renowned universities such as TELECOM ParisTech and other European Universities such as the Polytechnic University of Turin, Aalto University (formerly Helsinki University of Technology), Munich University of Technology and the Norwegian University of Science and Technology.

EURECOM benefits from a strong interaction with the industry through its specific administrative structure: Economic Interest Group (consortium type of structure), which brings together international companies such as: Orange, ST Microelectronics, BMW Group Research & Technology, Symantec, Monaco Telecom, SAP, IABG. The Principality of Monaco is an institutional member which joined the consortium at the beginning of 2013.

More about EURECOM at http://www.eurecom.fr

The department of Digital Security focuses on security and privacy requirements raised by emerging areas in communication and computer systems and tries to come up with solutions by designing new security mechanisms and privacy-preserving techniques to meet these requirements. While the main activity in this department consists of the detection, capture and analysis of malicious behavior as part of system and application software and embedded systems, there is a significant counterpart focusing on the design of new countermeasures for distributed software applications, communication systems, and digital media using applied cryptography, security protocols and signal processing.



Dans cette rubrique

(c) GdR 720 ISIS - CNRS - 2011-2015.