Google releases beta version of SynthID to identify AI images

In order to fight disinformation, the tech giant - Google is testing a digital watermark to identify images made by Artificial Intelligence (AI). In partnership with Google Cloud, a beta version of SynthID is being released to a limited number of Vertex AI customers using Imagen, Google’s own image generator tool.  

Google’s AI arm, DeepMind has developed SynthID that will identify images generated by machines. This technology embeds a digital watermark directly into the pixels of an image, making it imperceptible to the human eye, but detectable for identification.

But DeepMind said it is not "foolproof against extreme image manipulation".

Generative AI technologies are rapidly evolving, and computer-generated imagery, also known as ‘synthetic imagery’, is becoming harder to distinguish from those that have not been created by an AI system.

Watermarks are designs that can be layered on images to identify them. From physical imprints on paper to translucent text and symbols seen on digital photos today, they’ve evolved throughout history. It is used to show ownership, as well as partially to make it trickier for the picture to be copied and used without permission.

The feature of SynthID is that it does not compromise with the image quality and allows the watermark to remain detectable, even after modifications like adding filters, changing colours, and saving with various lossy compression schemes — most commonly used for JPEGs.

SynthID uses two deep learning models — for watermarking and identifying — that have been trained together on a diverse set of images. The combined model is optimised on a range of objectives, including correctly identifying watermarked content and improving imperceptibility by visually aligning the watermark to the original content.