Skip to content
AImpact
IT EN
Safety Intermediate Also known as: Filigrana AI

Watermarking

A technique that embeds an invisible statistical signal into text or images generated by a model, so they can later be identified as AI-produced.

ShareLinkedInX

In practice

Google's SynthID, for example, marks Gemini's text and images. Useful against disinformation, deepfakes, and plagiarism. Limit: it often breaks under rewrites, translation, or minor edits, and works only if the provider cooperates.

Related terms

Safety classifier Model extraction

Seen in the wild

1 entries mentioning it
  1. Executive Order 14110: the first comprehensive US federal AI safety regulation
    Landmark
← All terms