US EditionThe Synthid Watermark Embedded in Content Generated by Gemini Can Be Removed.
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
The "reverse-SynthID" project, which conducts research on watermarks, has demonstrated that it is possible to neutralize (remove) the digital watermarks embedded in images and text generated by Google's AI, Gemini, that indicate that they are AI-generated.
Google DeepMind identifies AI-generated images from Gemini with SynthID, an invisible watermark. Small changes that are not perceptible to the human eye are embedded in the image data, so that special tools (and now also Gemini) can recognize the origin. An independent developer now wants to have partially developed this system back. The open source project reverse-SynthID on GitHub pursues an unusual approach. The author created several hundred…
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
