A field guide to AI positions

Digital watermarking

Using AI.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2024-11-20

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

Information embedded in text, images or audio to help identify its origin. A watermark can be missed, removed or wrongly detected. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-watermarking-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

A watermark differs from a separate metadata record. Its presence does not establish that a claim is true, and its absence does not establish that a human made the content. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-watermarking-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

A watermark places a signal inside the content itself. It might be a visible mark or a subtle pattern detectable by software. Some schemes indicate that a particular generator produced the content. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-watermarking-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Map context: watermarking is one approach to documenting media origins. It does not tell us where an actor belongs on the map. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-watermarking-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/watermarking/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Reducing Risks Posed by Synthetic Content: An Overview of Technical Approaches to Digital Content Transparency

    National Institute of Standards and Technology · First-hand source · Published 2024-11-20 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2024-11-20

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read the introduction, selected provenance/detection passages and Appendix D's audio/video examples. Date checked on NIST's landing page. No detector certified here.

    Source ID: nist-synthetic-content

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide