Digital watermarking
Digital watermarking is the embedding of visible or invisible identifying information into digital content to indicate, verify, protect, or trace its origin or ownership.
Introduction to Generative AI, Second Edition
A watermark is a visible or embedded mark placed in an image or other media to indicate ownership, origin, or authenticity.
- How it is used
- Uses watermarking to help verify synthetic media at creation rather than relying only on later detection.
- How deep it goes
- Explains visible and hidden marks and text word-choice bias intuitively, without implementation instructions.
- Examples
- Illustrates pixel-embedded SynthID, word-choice-based SynthID-Text, and altered Getty Images marks in generated images.
- What you can do after
- Evaluate/understand watermark signals as useful origin clues whose absence or alteration cannot settle whether content was AI-generated.
Read how Introduction to Generative AI, Second Edition explains digital watermarking →
How Large Language Models Work
Watermarking is the process of embedding an identifiable signal or alteration in content to indicate its origin or authenticity.
- How it is used
- Uses identifiable alterations to distinguish generated content and reduce its unnoticed reuse in training data.
- How deep it goes
- Defines watermarking and gives a homoglyph example, but stops short of specifying a robust image-watermarking algorithm.
- Examples
- Uses subtle output changes and homoglyphs as examples, with teachers needing more reliable generated-content identification.
- What you can do after
- Evaluate watermarking as a practical identification aid while recognizing uncertainty about how reliably it works.
Read how How Large Language Models Work explains digital watermarking →
Related concepts
- provenancealternative to · Provenance is information about the origin and history of data or artifacts, including their sources, derivation, transformations, and movement.
- response generationuses · Response generation is the computational process by which a language model produces a natural-language answer or other output conditioned on an input, instructions, or context.
- SynthIDincludes · SynthID is Google's technology for embedding and detecting imperceptible digital watermarks in AI-generated content.
- noiseaddresses · Noise is variation, content, or data treated as unwanted, irrelevant, or distinct from the signal, pattern, or structure of interest.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.