Chandra, B.
, Dunietz, J.
and Roberts, K.
(2024),
Reducing Risks Posed by Synthetic Content An Overview of Technical Approaches to Digital Content Transparency, NIST Trustworthy and Responsible AI, National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.AI.100-4, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=959123
(Accessed December 13, 2024)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Reducing Risks Posed by Synthetic Content An Overview of Technical Approaches to Digital Content Transparency
Published
Author(s)
, ,
Abstract
This report examines the existing standards, tools, methods, and practices, as well as the potential development of further science-backed standards and techniques, for: authenticating content and tracking its provenance; labeling synthetic content, such as using watermarking; detecting synthetic content; preventing generative AI (GAI) from producing child sexual abuse material or producing non-consensual intimate imagery of real individuals (to include intimate digital depictions of the body or body parts of an identifiable individual); testing software used for the above purposes; and auditing and maintaining synthetic content.Citation
NIST Trustworthy and Responsible AI - 100-4
Report Number
100-4
Pub Type
NIST Pubs
Download Paper
Keywords
Generative AI, watermarking, synthetic content, digital content transparency, provenance, provenance data track, training data, metadata recording, , synthetic content detection
Citation
Issues
If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.
Created November 20, 2024