En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR5216-CHRROM-013 - (H/F) Niveau Ingénieur d'Etudes - Investigation légale des images numériques par l'apprentissage profond

(H/F) Engineer level - Digital image forensics via deep learning

This offer is available in the following languages:
Français - Anglais

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UMR5216-CHRROM-013
Date of publication : Tuesday, September 15, 2020
Type of Contract : FTC Technical / Administrative
Contract Period : 6 months
Expected date of employment : 1 November 2020
Proportion of work : Full time
Remuneration : 2088,66 € à 2206,09 € according to experience
Desired level of education : 5-year university degree
Experience required : Indifferent


With the increasing popularity and sophistication of photo editing software, our trust on authenticity of digital images is decreasing. Our objective is to develop an image forensic method based on the deep learning approach for the classification of authentic and fake images. More precisely, we would like to find answers to the following questions:
- Is the deep learning approach a suitable technical tool to solve image forensic problems?
- What is the most appropriate deep architecture in image forensic tasks?
- Are the features learned at different layers meaningful and, more importantly, helpful to understand the difference between authentic and fake images?


- Start with a brief literature review, on both image forensics and deep learning.
- Get familiar with one popular and representative deep learning software library such as PyTorch and TensorFlow, as well as the different varieties of deep learning architectures.
- Implement and test the performance of different deep learning architectures in image forensics, and gain some experience in how to select good architecture and how to do fine tuning.
- Try to understand the features learned at different layers of the deep learning architectures.


- Qualified candidates should have a Master/Engineer degree in Computer Science or related fields.
- Experience in multimedia security and/or machine learning will be a plus.
- Proficiency in Python programming.
- Excellent communication skills and strong motivation.

Work Context

Gipsa-lab is a CNRS research unit joint, Grenoble-INP (Grenoble Institute of Technology), University of Grenoble Alpes. It has agreement with Inria, Observatory of Sciences of the Universe of Grenoble.

With 350 people including 150 Ph.D students, Gipsa-lab is a multidisciplinary research unit developing both basic and applied researches on complex signals and systems.

Gipsa-lab develops projects in the strategic areas of energy, environment, communication, intelligent systems, life and health and linguistic engineering.

Thanks to its research activities, Gipsa-lab has a constant link with the economic environment through a strong partnership with companies.

Gipsa-lab staff is involved in teaching and training in different departments and engineering schools of the Grenoble academic area (Université Grenoble Alpes).

Gipsa-lab is internationally recognized for the research achieved in Automatic & Diagnostics, Signal Image Information Data Sciences, Speech and Cognition. The Lab is organized in 16 teams in 4 centers
.Automatic & Diagnostic
.Data Science
.Geometry, Learning, Information and Algorithms
.Speech -cognition

Gipsa-lab : 150 permanent staff and around 250 no-permanent staff (Phd, post-doctoral students, visiting scholars, trainees in master…)

The work will take place in the AGPIG (Architecture, Géométrie, Perception, Images, Gestes) team of GIPSA-lab, and will be supervised by Dr. Kai WANG. Working language can be either French or English.

We talk about it on Twitter!