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

if you tell it to generate the AI image with a black background you can visually see the synthid with a good enough monitor, it's just a repeating fuzzy pattern, nothing special.

I have found great success of getting rid of it by masking every 2nd pixel, regenerating missing pixels and then once again masking every 2nd pixel offset by 1.

Used an off the shelf model to fill in the pixels, but I also exported a depthmap first (before any alternations) and denoised it so generated masked pixels comform to the original content. The result was obviously not 100% perfect, but with more time and a model fine tuned for this specific use-case would be able to remove any kind of ai watermarking without too many issues.

What information is included in the metadata or SynthID? How many bits can be encoded in a SynthID?

Can it be used to create something like nutritional labels for synthetic content? 10% synthetic text, 30 synthetic images.

Your reality was 15% synthetic today (75% mega corp, 25% open-weight neocloud).

This is just performative nonsense.

As someone that creates things with tools with different media I would just hard avoid this tool that adds...

arbitrary metadata not of my choosing.

Should I seriously make a texture for a videogame with this weird DRM glorp in it?

How old is photoshop and why is it exempt?

Currently, this article is conveniently right next to it: https://news.ycombinator.com/item?id=48200569

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

First they verify whether a picture came from OpenAI, then they'll include subscriber data and geolocation.

Well, they'll finally find out that no one wants to look at AI generated pictures or text. Once they do that, the tool will fail for the public and only work for the government.

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.

Well that's not very useful. I think that can easily be hacked and many people were doing that frankly

While these are great, isn’t the problem that malicious actors will create systems that do not use synthID

What if they use advanced evasion techniques like printing it out and scanning it or taking a photo with their phone?

Is there no way to do this without uploading it?

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...

What happens if you generate an image with only a single pixel color or say two colors?

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

[dead]