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

1–10 of 198 posts

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

#3

Post by CSMastermind »

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.

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

#4

Post by Tiberium »

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 this also modifies the original.

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

#5

Post by amazingamazing »

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.

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

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

#8

Post by snissn »

amazingamazing wrote: post #5
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.

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

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

#9

Post by Arnt »

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.

This one was released a few years ago and still seems unbroken. I'm sure it will be broken at some point, but if you have to wait a year or two from when you make a deepfake until you can post it on Facebook, maybe that's enough. Maybe even a month is enough.
Post reply on HN