This thesis is granted by a National French project.
The application must include:
Applications should be submitted by e-mail to firstname.lastname@example.org
Education Level / Degree: Computer Engineering or Master Degree (with honors);
English is mandatory, French is just a plus.
EURECOM benefits from a strong interaction with the industry through its specific administrative structure: Economic Interest Group (kind of consortium), which brings together international companies such as: Swisscom, SFR, Orange, ST Microelectronics, BMW Group Research & Technology, Symantec, Monaco Telecom, SAP, IABG.EURECOM is a French graduate school and a research center in communication systems based in the international science park of Sophia Antipolis, which brings together renowned universities such as Télécom ParisTech, Aalto University (Helsinki), Politecnico di Torino, Technische Universität München (TUM), Norwegian University of Science and Technology (NTNU), Vietnam National University Ho Chi Minh Ville (VNU) and Chalmers University (Sweden). The Principality of Monaco is a new institutional member. The Institut Mines-Télécom is EURECOM’s founding member.
EURECOM deploys its expertise around three major fields: Networking and security, Multimedia Communications and Mobile Communications. EURECOM is particularly active in research in its areas of excellence while also training a large number of doctoral candidates. Its contractual research is recognized across Europe and contributes largely to its budget.
Thanks to its strong ties set up with the industry, EURECOM was awarded the “Institut Carnot” label jointly with the Institut Telecom right from 2006. The Carnot Label was designed to develop and professionalize cooperative research. It encourages the realization of research projects in public research centers that work together with socioeconomic actors, especially companies.
Image forensics includes two major challenges:
Even if image forensics is quite a new topic, some commercial products already exist. Nonetheless, several open problems still exist:
In this work, the Ph.D student will mainly focus on the automatic detection of image manipulations, according to the following three axes:
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).
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:
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
J.A. Redi, W. Taktak, J.-L. Dugelay
J. Multimedia Tools and Applications 51 (1), 133-162
(c) GdR 720 ISIS - CNRS - 2011-2015.