How SI content can be labelled at the source: signed Content Credentials based on the C2PA standard, invisible watermarks such as Google's SynthID, and the plain metadata fields that declare a synthetic image. These articles explain what each system proves, who can read it and why it so often disappears on the way to your screen. Our SI image detector reads C2PA manifests, XMP flags and EXIF data when they survive, and falls back on pixel analysis when they do not.
C2PA Content Credentials are signed provenance data that record which tool made a file and how it was edited. Here is how they work, how to check them, and what happened when we removed them from ten ChatGPT photos.
Read the articleSynthID is Google DeepMind's invisible watermark for content made by Google's SI (AI) models. Here is how it works for text, images, audio and video, who can check for it, where it fails, and how it compares with C2PA Content Credentials.
Read the article
