I don't understand all the handwringing. If it's this easy to remove SynthID from an AI-generated image then it wasn't a good solution in the first place.

▲

raincole 2 hours ago | parent | next [-]

There is no solution. I don't know why people discuss this subject as if there is a technical solution. As if there are fairies or souls hidden in the pixels that help us tell what is AI generated and what is not.

▲

DonsDiscountGas 2 hours ago | parent | next [-]

If you want to make an AI generated image but don't want other people to know that it's AI, the most obvious solution is to not use Gemini. Synth ID is watermarking. It's only ever going to be useful to good actors, who want an AI generated image and aren't trying to hide the fact that it's AI generated.

	▲	dummydummy1234 an hour ago \| parent [-]
		Never underestimate that people are lazy.

▲

sodacanner 2 hours ago | parent | prev | next [-]

Sure, and things like this help drive home that SynthID wasn't a solution at all.

▲

levocardia 2 hours ago | parent | prev [-]

Sure there is a solution, you are just looking at it the wrong way. Make non-AI images provably unaltered with signed keys from the device (e.g. the camera) that took it.

▲

jfim an hour ago | parent | next [-]

That's pretty much impossible though.

One workflow that some artists use is that they draw with ink on paper, scan, and then digitally color. Nothing prevents someone from generating line art using generative AI, printing it, scanning it, and coloring it.

And what if someone just copy pastes something into Photoshop or imports layers? That's what you'd do for composites that mix multiple images together. Can one copy paste screenshots into a multi layer composition or is that verboten and taints the final image?

And what about multi program workflows? Let's say I import a photo, denoise it in DxO, retouch in affinity photo, resize programmatically using image magick, and use pngcrush to optimize it, what metadata is left at the end?

▲

raincole an hour ago | parent | prev | next [-]

If the premise is that everyone would just agree on the same protocol, I have an even more unbreakable solution: every image has to be upload to a blockchain the moment it is (claimed to be) created. Otherwise it's AI.

If only everyone just agrees with me.

▲

Diggsey an hour ago | parent | prev | next [-]

Which works for about 5 minutes until someone leaks a manufacturer's private key or extracts it from a device...

▲

IncreasePosts an hour ago | parent | prev [-]

How many minutes do you think it would take before someone figured out how to crack that?

▲

subscribed an hour ago | parent [-]

On Pixels and iPhones it would be impossible since they have actually secure hardware that could both hold the keys and sign/verify the image.

	▲	IncreasePosts an hour ago \| parent [-]
		The camera module sits outside the secure area, meaning it would need to send data in to be signed. How does the phone know that it's getting legitimate data from the camera module, or data someone else is just piping in? Also, you could probably get a fairly high quality image by just taking a photo of something AI generated in the right lighting conditions.

▲

rustyhancock 2 hours ago | parent | prev [-]

Yes. This kind of project needs aggressive red teaming, it leads to better products and we need excellent products in this space.

This project proves what red teaming was in place wasn't good enough.