Has Google’s AI watermarking system been reverse-engineered? www.theverge.com/ai

A software developer claims to have reverse-engineered Google DeepMind's SynthID system, showing how AI watermarks can be stripped from generated images or manually inserted into

Google will still embed invisible SynthID and C2PA watermarks into AI-generated images, videos, and music. www.theverge.com/tech/980416/...

AI content is getting good, but SynthID might be able to help tell truth from fiction.

<a href="https://news.ycombinator.com/item?id=48198291">Comments</a>

The company is changing its download policy and rolling out new watermarking technology. www.theverge.com/ai-artificia...

Even with Google’s watermarks and restrictions, a tool that creates believable flyover images is ripe for misuse, as Henk van Ess has already shown.