PhD position on Deepfake detection and attribution

The Idiap Research Institute seeks qualified candidates for a PhD position on "Deepfake detection and attribution".

Recent advances in Deep Learning enabled for the automatic generation of hyper-realistic fake media content coined as Deepfakes. While this technology has positive potential for entertainment applications, malicious use of this technology has been already reported to harm citizens and the society at large by producing obscene content, broadcasting fake news to undermine elections or de-stabilise politics and improving social engineering to commit financial fraud. The severity of the problem calls for the urgent development of Deepfake detection technologies for media companies, multimedia news providers and Law Enforcement Agencies. Also as Deepfakes encompasses several categories of synthetically altered or generated media, a secondary objective is to identify the type of manipulation and the specific technology employed for that purpose this is referred to as attribution.

The objective of this PhD thesis is to develop Deepfake detection and attribution algorithms. Novel research directions in one class modeling, spatio-temporal learning, few-shot learning, and adversarial training will be explored.

The proposed research will be carried out in the Biometric Security and Privacy group (Dr. Sebastien Marcel),  at Idiap. The research will also be co-supervised by Prof. Christophe Champod, School of Criminal Justice / Ecole des sciences criminelles (ESC), Faculty of law, criminal justice and public administration of the University of Lausanne. The research will rely on previous knowledge and software developed at Idiap, more specifically Bob toolkit. Reproducible research is a cornerstone of the project. Hence a strong involvement in open source libraries such as Bob are expected.

The ideal candidate should hold a Master degree in Computer Science, Forensic Science or related fields. She or he should have a background in statistics, applied mathematics, optimization, linear algebra and signal processing. The applicant should also have strong programming skills and be familiar with Python, C/C++ (MATLAB is not a plus), various scripting languages and with the Linux environment. Knowledge in machine learning and more particularly deep learning (TensorFlow and pyTorch) is an asset. Short-listed candidate may undergo a series of tests including technical reading and writing in English and programming (in Python and/or C/C++).

Working at Idiap in Martigny, the successful candidate will registered as a doctoral student at University of Lausanne (UNIL), affiliated with the School of Criminal Justice / Ecole des sciences criminelles (ESC), and has to be accepted as a UNIL Doctoral student. The PhD position is for 4 years, provided progress and a successful candidacy exam on the first year, and should lead to a dissertation. Additionally the PhD student should obtain 12 ECTS credits in Forensic Science before completion of the PhD. Annual gross salary ranges from 47,000 CHF (first year) to 50,000 CHF (last year).

Prospective candidates should apply through the Idiap Online Recruitment System (ORS) here PhD position on Deepfake detection and attribution. The applications should contain a cover letter (max 2 pages long and should explain how your background fit with our research activities, see the short description of our research and our latest publications), CV, statement of research interests and accomplishments, and names and email addresses of 3 references. Inquiries about the position can be addressed to Dr. Sebastien Marcel.

The project start date is expected to be early 2021. The position will remain open until filled.