Authenticity & Provenance in the age of Generative AI

OVERVIEW

Generative AI allows for the rapid and automatic generation of highly realistic audio, images, and videos (so-called deepfakes). The field of media forensics and digital provenance focus on detection and authentication of this content, thus helping in mitigating the potential risks. This workshop aims at bringing a heterogeneous group of specialists from academia, industry, and civil society together to discuss emerging threats, technologies, and mitigation strategies. The workshop will focus on the application of tools from computer vision, pattern recognition, and machine learning, as well as the development of novel approaches for verifying the integrity and tracing the origins of digital media, the creation of novel datasets for evaluation, large-scale evaluations of existing forensic techniques, and ethical/policy considerations around generative AI and forensic techniques.

Topics

• media forensics (audio, image, and video)

• 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

safe: sYNTHETIC vIDEO dETECTION cHALLEnGE

We are launching a new evaluation challenge at ICCV2025 to advance the state of the art in detecting and attributing fully synthetic video content. As generative video technologies rapidly evolve, this effort will help assess and strengthen algorithmic capabilities in identifying synthetic media across diverse and complex scenarios. Sponsored by the ULRI Digital Safety Research Institute, the challenge aims to drive innovation in scalable, generalizable, and resilient detection methods. Learn more.