Synopsis:
Recent advances in artificial intelligence, especially Generative AI, for media creation and manipulation enable 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 risk infringing copyrights and spreading manipulated media, such as deepfakes, which often lead to social unrest, the spread of rumours for political gain, or the encouragement of hate crimes.
The talk aims to discuss the current advances in trustworthy media generation, distribution and consumption.
This talk also describes the JPEG Trust international framework (ISO/IEC 21617) that aims to establish trust in digital media creation, modification, annotation, distribution and consumption.
The framework provides standardized protocols to extract indicators to assess trustworthiness, means to annotate media provenance, and securely link the assets and associated annotations together.
Media manipulation can be traced back over 150 years to 1860, when Abraham Lincoln’s head was placed on John Calhoun’s portrait.
While typically, media manipulations are seen as malpractices, manipulations are commonplace in wider usage scenarios, starting from editing for entertainment and creative industries (legitimate) to gaining political advantages, spreading misinformation or harming others’ reputations and finances.
Massive technological development in software toolsets and recent advancements in AI technology, particularly generative AI, have created a disruptive inroad over the last few years that permits near-realistic synthetic content modification and generation with ease.
Drawing reliable conclusions about the authenticity of digital media is complicated and becoming more so as Generative AI start appearing. Consumers of social media are 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, with risks of real-world consequences.
Addressing such a complex issue, requires both algorithmic development and a successful adaptation in the daily life. This prompts the need for an international standard which can enable global interoperable media asset authenticity and JPEG (Joint Photographic Experts Group) led that development through their newest proposed standard ‘JPEG Trust’. JPEG Trust defines a framework for establishing trust in media.
This framework addresses aspects of authenticity, provenance and integrity through secure and reliable annotation of media assets throughout their life cycle.
This talk will provide the landscape of media authenticity, including content authentication, deep fake and AI-generated image detection techniques along with the description of the JPEG Trust standard.

source