comscore
17 Feb, 2024 | Saturday
Trending : LaptopsAppsAutomobileHow ToOPPO India

Google is making it easy to tell AI-generated images apart

In partnership with Google Cloud, Google DeepMind (Google’s AI research division) has launched a beta version of a new tool called SynthID.

Edited By: Shubham Verma

Published: Aug 31, 2023, 06:01 PM IST

Google DeepMind said the watermark is detectable even after modifications like adding filters, changing colours and brightness.
Google DeepMind said the watermark is detectable even after modifications like adding filters, changing colours and brightness.

Story Highlights

  • Google DeepMind has partnered with Google Cloud to launch a new tool called SynthID.
  • SynthID will help humans distinguish between real and AI-generated images easily.
  • Google DeepMind, however, said SynthID isn’t foolproof against extreme image manipulations.

Google has launched a new tool for watermarking and identifying AI-generated images — a technology that embeds a digital watermark directly into the pixels of an image, making it imperceptible to the human eye but detectable for identification. In partnership with Google Cloud, Google DeepMind (Google’s AI research division) has launched a beta version of a new tool called SynthID. This tool will help humans distinguish between real and AI-generated images easily. However, Google DeepMind states caution while using the tool as it is not entirely foolproof.

SynthID is available to a limited number of Vertex AI (Google’s platform for building AI apps and models) customers using Imagen, one of the company’s latest text-to-image models that use input text to create photorealistic images.

“While generative AI can unlock huge creative potential, it also presents new risks, like enabling creators to spread false information — both intentionally or unintentionally,” Google DeepMind said in a blog post. “Being able to identify AI-generated content is critical to empowering people with knowledge of when they’re interacting with generated media, and for helping prevent the spread of misinformation,” it added.

According to DeepMind, SynthID remains in place even after modifications, such as adding filters to images, changing their colours, and compressing them. In order to produce the tool, DeepMind trained two AI models together on a “diverse” set of images, one for watermarking and one for identification. However, SynthID cannot confidently identify watermarked images. The tool distinguishes between images that may or may not have a watermark and images that are highly likely to have one.

“SynthID isn’t foolproof against extreme image manipulations, but it does provide a promising technical approach for empowering people and organisations to work with AI-generated content responsibly. This tool could also evolve alongside other AI models and modalities beyond imagery such as audio, video, and text,” Google said. This tool provides three confidence levels for interpreting the results of watermark identification. If a digital watermark is detected, part of the image is likely generated by Imagen. The company mentioned that it will integrate the tool into more Google products and make it available to third parties in the near future.

— Written with inputs from IANS

Get latest Tech and Auto news from Techlusive on our WhatsApp Channel, Facebook, X (Twitter), Instagram and YouTube.

Author Name | Shubham Verma

STAY UPDATED WITH OUR NEWSLETTER

Select Language