PhD Position or Postdoc Computer Vision / Deep Learning: Deepfake Detection

Context

Inria, the French National Institute for computer science and applied mathematics, promotes “scientific excellence for technology transfer and society”. Graduates from the world’s top universities, Inria's 2,700 employees rise to the challenges of digital sciences. With its open, agile model, Inria is able to explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of the digital transformation. Inria is the source of many innovations that add value and create jobs.
Team
The STARS research team combines advanced theory with cutting edge practice focusing on cognitive vision systems.
Team web site :
https://team.inria.fr/stars/

Assignment

The Inria STARS team is seeking for a Ph.D. or postdoctoral researcher with strong background in computer vision, deep learning and machine learning.
The candidate is expected to conduct research related to deepfake detection.

Main activities

Context.
The position is in the STARS team at the Inria Centre at Université Côte d’Azur (Sophia Antipolis), within a collaborative project with an industrial partner specializing in the analysis of online disinformation. Generative AI tools for images, voice, and video are now easy to use, and a growing share of the content in influence campaigns is synthetic and hard to detect. The project aims to advance the automatic detection of AI-generated videos and to transfer the resulting methods to operational tools.
Topic.
The research will focus on detecting AI-generated videos, especially talking-face deepfakes. Current detectors degrade on compressed footage and on content from unseen generators, such as recent diffusion models, so the main goal is generalization. Key directions include audio-visual consistency through lip-reading embeddings, temporal and physiological cues, and using the team’s own video generation models to build diverse training data. The detectors should be robust to social media degradations and produce calibrated outputs so they can be fused with audio and image detectors. The candidate will evaluate the methods on real-world data and publish in top computer vision and biometrics venues.

Skills

Candidates must hold a Master degree or equivalent in Computer Science or a closely related discipline by the start date.
The candidate must be grounded in the basics of computer vision, have solid mathematical and programming skills.
Preferably in Python, OpenCV, deep learning framework Pytorch or Tensorflow.
The candidate must be committed to scientific research and strong publications.