Google's SynthID Detector identifies AI-generated media from OpenAI, Nvidia, and Kakao
Google has launched the SynthID Detector, a tool that identifies AI-generated images, video, and audio by detecting invisible watermarks embedded during creation. It supports media from Google, Nvidia, OpenAI, and Kakao, and remains effective after common edits like compression or filters. Unlike general AI detectors, it verifies an intentional signal rather than guessing from artifacts, but it only works with partner models and isn't foolproof.
This is not a general AI detector. We can only detect media from the above companies, who have adopted SynthID technology.
- Tiberium
It's baffling that this requires auth. OpenAI's own tool (https://openai.com/research/verify/) doesn't require auth.
Even Google themselves previously offered a no-auth way (just very niche): if you uploaded an image to Google Image search, and went to "About this image", it would show if the image was Google AI-generated. Now it doesn't.
- Retr0id
It's a real shame Google isn't more transparent about how it actually works, and doesn't provide any mechanism for classifying images in bulk or offline.
This is the best SynthID write-up I've found so far: https://fyx.me/articles/attempting-model-extraction-of-googl...
It covers how it actually works (probably), and how to train your own classifier for it, with some seemingly decent results.
- jdranczewski
Finally, the previous implementations were very silly! OpenAI had a nice tool, but it only detected their own watermarks, and Google's process was "upload the image to Gemini and ask if it's AI generated", which seemed like a perplexing waste of tokens and breath.
(While a sibling comment points out putting the image through Google Image Search as an alternative, I don't remember this being signposted in the support article I've read, so I unfortunately didn't know about it)
- HelloUsername
https://blog.google/innovation-and-ai/models-and-research/go...
- nialv7
Why the hell do I need to sign in?