Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

openai.com

Post reply on HN
Print view View original

11–20 of 198 posts

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#11

Post by cephei »

snissn wrote: post #8
amazingamazing wrote: post #5

Earlier quoted context omitted.

No, they are very resistant to modification that can be done easily. That being said I doubt it is impossible

I’m surprised! I guess I’m being naive but I would imagine you could pass an image to an image model without synthid and have it reconstruct the image in a net new way without the markers. I guess I’m wrong? That’s cool if the watermarks are so deeply ingrained that they persist

As I understand it, they modify the image by applying a special Gaussian noise filter which affects each pixel in the image in subtle (possibly not reversible) ways. The detecting service will look for this noise pattern to flag it, so even a part of the image is enough to know it was generated by AI.

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#12

Post by minimaxir »

I'm annoyed that Google is keeping it closed-sourced and limited to partners. Is there a negative externality about open-sourcing image watermark technology so anyone can use it and audit the watermarks independently? If not, then I may have a repository for an open-source invisible and tamper-resistant image watermarking approach that's feature complete...

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#13

Post by parhamn »

minimaxir wrote: post #12

I'm annoyed that Google is keeping it closed-sourced and limited to partners. Is there a negative externality about open-sourcing image watermark technology so anyone can use it and audit the watermarks independently? If not, then I may have a repository for an open-source invisible and tamper-resistant image watermarking approach that's feature complete...

might be easier to strip it?

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#14

Post by raincole »

amazingamazing wrote: post #6

Good. Despite people saying it will be removed, I have seen no reproducible repo demonstrating it.

Stable Diffusion with 10%~15% denoising strength. Done.

I tested the day 1 when Nano Banana Pro was released and it worked. It still works today for Nano Banana 2.

I didn't post this anywhere because I (arrogantly) thought saying it publicly would make the internet worse. But it was pure arrogancy: if I came up with this the first day then of course other millions of programmers did too.

That being said, it'll introduce the typical artifacts from SD models and that might be detected by other methods (or just by zooming in a lot and looking carefully).

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#16

Post by pta2002 »

PunchyHamster wrote: post #2

so ? people wanting to make AI propaganda will just make tool to remove it. Possibly using AI to do it too

I assume a selfish benefit is that OpenAI and Google don't want the models to train on their own data. There is just /so much/ AI generated content online that they definitely need to filter it out somehow when assembling the training data. This is a pretty effective way to do that, with the nice bonus of being mostly good from a PR standpoint.

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#17

Post by vunderba »

raincole wrote: post #14
amazingamazing wrote: post #6

Good. Despite people saying it will be removed, I have seen no reproducible repo demonstrating it.

Stable Diffusion with 10%~15% denoising strength. Done. I tested the day 1 when Nano Banana Pro was released and it worked. It still works today for Nano Banana 2. I didn't post this anywhere because I (arrogantly) thought saying it publicly would make the internet worse. But it was pure arrogancy: if I came up with this the first day then of course other millions of programmers did too. That being said, it'll introd…

Yup, OOC a while back I put together a ComfyUI node that took in a NB image and start with the smallest amount of denoise strength using Flux.1 (but works with any model), then run img2img with a synthid check incrementing denoise in a loop until it was defeated.

Never released it, but it was obvious to most people in the SD community that denoising using a diffusion model was a relatively trivial means to beat most steganographic watermarks.

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#18

Post by programd »

CSMastermind wrote: post #3

Aren't these kinds of watermarks easy to remove or distort? Seems like they're only helpful as long as people are relying on them sparingly so it's not worth the effort to circumvent. If social media platforms started banning images with these watermarks seems like they'd be stripped out overnight.

Define easily. There is an approach that apparently works and is based on spectral analysis of the images.

https://github.com/aloshdenny/reverse-SynthID

Re: OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

#20

Post by vunderba »

Tiberium wrote: post #4
CSMastermind wrote: post #3

Aren't these kinds of watermarks easy to remove or distort? Seems like they're only helpful as long as people are relying on them sparingly so it's not worth the effort to circumvent. If social media platforms started banning images with these watermarks seems like they'd be stripped out overnight.

I still don't think there's a single GitHub repo that actually removes real SynthID watermarks from Nano Banana 2/NBPro outputs. Most of them are just some research projects that haven't achieved this. The only methods so far I've seen are weird tricks with transparency/overlaying the original image if you're using edits, and also using a diffusion model to regenerate the NB-generated image at low noise levels, but t…

Right I think that’s why you probably need to start with very low levels of denoising and experiment with different approaches.

Set up as a ComfyUI workflow that does a few things: it tries SDXL, Flux, and a couple of different denoising methods at the lowest possible strength (progressively incrementing) to avoid changing the image too much, while also running a SynthID check each time, and repeating this in a loop until the watermark is essentially gone.

At the same time, you’d probably want to add some kind of threshold based on a perceptual hash aka the maximum perceptual quality difference you’re willing to accept.

Post reply on HN