Context

Recent advances in artificial intelligence, especially deep learning, for media manipulation enables users to produce near-realistic media content that is almost indistinguishable from authentic content to the human eye. These developments open a multitude of opportunities, from creative content production, the art industry, and digital restoration to image and video coding. However, they also lead to the risk of the spread of manipulated media such as deepfakes which often lead to copyright infringements, social unrest, the spread of rumours for political gain or encouraging hate crimes.

As a result, consumers are more and more challenged to assess the trustworthiness of the media they encounter, and agencies that depend on the authenticity of media assets must be concerned with mistaking fake media for real.

To address this problem and to provide leadership in global interoperable media asset authenticity, JPEG initiated development of a new international standard: JPEG Trust. JPEG Trust defines a framework for establishing trust in media. This framework adresses aspects of authenticity, provenance and integrity through secure and reliable annotation of media assets throughout their life cycle.

JPEG Trust arises from a four-year exploration of requirements for addressing mis- and dis-information in online media, followed by a 2022 Call for Proposals, conducted by international experts from industry and academia from all over the world.

This workshop, organized in Covilhã, Portugal, on the 19th of July 2023, further explored the relation between media authenticity and generative AI and assess the role of standardization in this challanging area.

Program

• 15:00-15:10 WEST - Welcome and Introduction (Touradj Ebrahimi, EPFL)
• 15:10-15:20 WEST - Overview of JPEG Trust (Frederik Temmermans, Vrije Universiteit Brussel & imec)
• 15:20-15:30 WEST - Overview of JPEG AI (João Ascenso, Instituto Superior Técnico)
• 15:30-15:50 WEST - Synthetic Realities: Challenges for Multimedia Forensics in the Era of Generative Artificial Intelligence (Anderson Rocha, University of Campinas)
• 15:50-16:00 WEST – Industry’s take on trust issues in AI (Xiaojun Gu, Huawei)
• 16:00-16:10 WEST - Identification of Generative Media (Leonard Rosenthol, Adobe)
• 16:10-16:30 WEST - Discussion panel (moderated by Fernando Pereira)

Proceedings

The presentations presented during the workshop are available for download here.

Referencing

JPEG Workshop on Media Authenticity in the Age of Artificial Intelligence Proceedings, ISO/IEC JTC1/SC29/WG1, wg1n100613, Covilhã, Portugal, June 19th, 2023.

More information

Interested parties are invited regularly consult the JPEG.org website for the latest news.