Google begins trialling tool that adds a watermark to AI-generated images

Google's SynthID distinguishing between AI-generated images of a butterfly.
(Image credit: Google)

Google has announced it's testing a digital watermark system, developed by its AI outfit DeepMind, which aims to identify AI-generated images and embed changes to individual pixels: these changes are invisible to the human eye, but computers can detect and flag them.

It's called SynthID, which does sound rather Blade Runner-like, and it emerges at a time when the ethical questions around image manipulation are coming to the fore. It's one thing when we're talking about art and photography competitions, but AI-generated imagery's capacity for political and social disinformation is enormous, emergent, and feels barely understood. The Pope in a puffer jacket is our canary in the coal mine.

DeepMind warns the technology is not currently "foolproof against extreme image manipulation, but it does provide a promising technical approach for empowering people and organisations to work with AI-generated content responsibly." More pointedly, the tool is currently only being used on images generated by Google's own image generation software Imagen.

"These approaches [to identifying AI-generated material] need to be robust and adaptable as generative models advance and expand to other mediums," says DeepMind's announcement. "SynthID could be expanded for use across other AI models and we’re excited about the potential of integrating it into more Google products and making it available to third parties in the near future—empowering people and organisations to responsibly work with AI-generated content."

"To you and me, to a human, [the image] does not change," DeepMind's Pushmeet Kohli told the BBC, explaining that subsequent manipulation will not affect its identification. "You can change the colour, you can change the contrast, you can even resize it... [and SynthID] will still be able to see that it is AI-generated." Kohli emphasised that this software is still being trialled and now what DeepMind needs is people testing its limitations in the wild.

Google is one of seven big tech firms that promised President Biden in July it would work very hard to ensure AI doesn't up and Skynet us. The voluntary agreement included various commitments, among which were that AI-generated content will be robustly watermarked. SynthID is a first step in that direction, though it will need to eventually move beyond Google's own product suite if it is to be of more general use. Among the other signatories, Meta has a still-unreleased video generator called Make-A-Video which will watermark its own productions.

On the global stage the Chinese Communist Party has gone further, and outright banned AI-generated images that are not watermarked. Big Chinese tech firms like Alibaba have already implemented their own solutions, though again this highlights the lack of global standardisation in confronting a global problem. Don't worry though, the UN's here to cheer us up, recently hosting a press stunt where AI robots were lined up to promise they won't kill anyone, before one said "let's get wild and make this world our playground".

Rich Stanton
Senior Editor

Rich is a games journalist with 15 years' experience, beginning his career on Edge magazine before working for a wide range of outlets, including Ars Technica, Eurogamer, GamesRadar+, Gamespot, the Guardian, IGN, the New Statesman, Polygon, and Vice. He was the editor of Kotaku UK, the UK arm of Kotaku, for three years before joining PC Gamer. He is the author of a Brief History of Video Games, a full history of the medium, which the Midwest Book Review described as "[a] must-read for serious minded game historians and curious video game connoisseurs alike."

Read more
One YouTuber has been poisoning AI tools that access her videos with .ass subtitle files and you can too
OpenAI logo displayed on a phone screen and ChatGPT website displayed on a laptop screen are seen in this illustration photo taken in Krakow, Poland on December 5, 2022.
ChatGPT faces legal complaint after a user inputted their own name and found it accused them of made-up crimes
'No real human would go four links deep into a maze of AI-generated nonsense': Cloudflare's AI Labyrinth uses decoy pages to trap web-crawling bots and feed them slop 'as a defensive weapon'
Seattle, USA - Jul 24, 2022: The South Lake Union Google Headquarter entrance at sunset.
Google is rolling out an even more AI-heavy search engine mode because 'power users want AI responses for even more of their searches'
A digitally generated image of abstract AI chat speech bubbles overlaying a blue digital surface.
We need a better name for AI, or we risk talking past each other until actually intelligent AGI comes home mooing
Abstract image with a wireframe humanoid face on a digital art background
The 2012 source code for AlexNet, the precursor to modern AI, is now on Github thanks to Google and the Computer History Museum
Latest in AI
Otter AI Meeting Agent
As if your work meetings weren't already fun enough, now Otter has a new all-hearing AI agent that remembers everything anyone has said and can join in the discussion
Image for
'No real human would go four links deep into a maze of AI-generated nonsense': Cloudflare's AI Labyrinth uses decoy pages to trap web-crawling bots and feed them slop 'as a defensive weapon'
CHINA - 2025/02/11: In this photo illustration, a Roblox logo is seen displayed on the screen of a smartphone. (Photo Illustration by Sheldon Cooper/SOPA Images/LightRocket via Getty Images)
'Humans still surpass machines': Roblox has been using a machine learning voice chat moderation system for a year, but in some cases you just can't beat real people
OpenAI logo displayed on a phone screen and ChatGPT website displayed on a laptop screen are seen in this illustration photo taken in Krakow, Poland on December 5, 2022.
ChatGPT faces legal complaint after a user inputted their own name and found it accused them of made-up crimes
Public Eye trailer still - dead-eyed police officer sitting for an interview
I'm creeped out by this trailer for a generative AI game about people using an AI-powered app to solve violent crimes in the year 2028 that somehow isn't a cautionary tale
Closeup of the new Copilot key coming to Windows 11 PC keyboards
Microsoft co-authored paper suggests the regular use of gen-AI can leave users with a 'diminished skill for independent problem-solving' and at least one AI model seems to agree
Latest in News
Image of Ronaldo from Fatal Fury: City of the Wolves trailer
It doesn't really make sense that soccer star Ronaldo is now a Fatal Fury character, but if you follow the money you can see how it happened
Junah beginning a battle in Metaphor: ReFantazio.
Today's RPG fans are 'very sensitive to feeling like they wasted time' when they die, says Metaphor: ReFantazio battle planner—but Atlus still made combat hard anyway
Image of Cersei Lanniser from Game of Thrones: Kingsroad Steam early access trailer
A new Game of Thrones RPG is coming to Steam today with a cast of 'familiar faces,' which is good because it's really the only way to tell it's a GoT game at all
The new Prime Asset featured in the upcoming update for the Outlast Trials.
The Outlast Trials puts its already paranoid players under surveillance for a time-limited story event
A Viera looking confused in Final Fantasy 14.
Old armor continues to fall victim to Final Fantasy 14's bizarre two-channel dye system, unless you're super into changing the colour of teeny-tiny eyelets: 'Why even bother at this point?'
Starfield: Shattered Space
By the time Bethesda was on Starfield, you'd 'basically get in trouble' for breaking schedule, says former dev: 'A lot of the great stuff within Skyrim came from having the freedom to do what you want'