Workshop on Media Forensics

OVERVIEW

Generative adversarial networks and diffusion-based synthesis allow for the rapid and automatic generation of highly realistic images and videos (so-called deep fakes). The increasing prevalence of fraud and misuse associated with such fabricated media, have raised the level of interest in the computer vision community. Both academia and industry have addressed this topic in the past, but only recently, with the emergence of more sophisticated ML and CV techniques, has multimedia forensics become a broad and prominent area of research. The recent appearance of relevant datasets (e.g., DFDC, FaceForensics++) and the widespread concerns surrounding synthetic media and misinformation, have turned the field of media forensics and misinformation into a critical research topic. This workshop aims at bringing a heterogeneous group of specialists from academia and industry together to discuss emerging threats, technologies, and mitigation strategies.

Topics

• media forensics

• media provenance

• counter-forensics

• analysis and detection of new media-synthesis methods

• forensic pattern analysis and identification

• ethics in data synthesis, manipulation, or forensics

• datasets