Google has created an invisible watermark to mark images generated by a neural network. SynthID will be invisible to humans, but will be detectable by special artificial intelligence tools. Google is going to present a novelty at the Google Cloud Next conference.
Google has developed SynthID, a tool that allows applying watermarks invisible to the human eye on images generated by a neural network. The Verge writes about this quoting Demis Hassabis, CEO of Google DeepMind.
The SynthID will be embedded in the image without modifying it. The watermark will not be seen by the human viewer, it can be detected using special artificial intelligence tools, and it cannot be edited to remove the watermark.
In a first stage, SynthID will be implemented in Google services: the cloud, the image generator. SynthID is expected to be officially unveiled at the Google Cloud Next conference in the coming days.
Author:
Kirill Bilyk
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
