Content Safety API
Classifier that finds novel abuse imagery and prioritizes it for review.
Made by GoogleCSAM detection
About Content Safety API
The Content Safety API is a Google tool that classifies previously unseen images and videos. The Content Safety API classifier uses programmatic access and artificial intelligence to help partners classify and prioritize billions of images and videos for review. Industry and civil society third parties seeking to protect their platform against abuse can sign up to access the Content Safety API, and applications are subject to approval.
The Content Safety API can be used in parallel with other solutions, such as YouTube's CSAI Match video hashing tool or Microsoft's PhotoDNA. Partners must conduct their own review in order to determine whether they should take action on the content.
Drafted from protectingchildren.google · not yet confirmed by Google
How it works
Google's Content Safety API is a classifier for never before seen CSAM. Hash matching only finds known material; this looks at an image and returns a priority score for how likely it is to be abuse imagery, so reviewers can look at the worst first. It's designed to reduce the volume of material a human has to see, not to make final decisions.
It's available free to partner organizations through the Protecting Children program, and it's typically run behind a hash match so known material is handled automatically and only novel candidates go to the classifier.
Reviews
Be the first to review it
AnonymousKnow a team weighing Content Safety API? Send them this page.