matyask

By unique we mean one of the numbers we can represent by 50 bits in each patch we encode plus some bits for error correction and some bits for noise, it's in the faq but we will explain it better. If the domain is all the encoded patches with a particular id then the mapping is surjective.

Thank you for the link and the excerpt!:)

1) With an invariant domain representation, 2) and 3) I am not certain yet, but I will find out.

Although when it comes to signing with a watermark for validity you would not want the id (50 bits) to be preserved or copied. These are separate use cases / applications.

I think you are making assumptions on provenance. The resource disparity you point out is obvious, but your phrasing somewhat binary. We have released a demo not a consumer product yet. I would be happy to hear your more expanded thoughts, especially on the threat model you have in your mind.

We for sure don't aim to be anti-AI. It's difficult to see how a non technical solution will be enforceable/effective. Watermarking is our initial approach to securing digital identity and copyrights.

Hi there, we have published a demonstration of fingerprint watermarking on audio and images that anyone could just try. In our next phase we will release our first consumer product that will provide value. We have conducted thorough testing on our fingerprint encoding and decoding. We will for sure aim to explain this better when we give users the ability to encode unique signatures.

If there are any other particular claim you have not found enough information about then I am happy to elaborate.

Could you by any chance link any of those court cases?

Hi, one of the founders here, "robustness" is our next step. We are currently training a few models based on cross attention and invariant domain learning that promise to be quite resistant to noising and denoising. The purpose of fingerprint watermarking as we have released it is to act like a signature for validity, some companies already do this but none of them have public products that you can just use. The nest encoder and decoder will use a unique signature for every user. The limitation of Glaze and models like it is that they target specific models/approaches. That being said we are also running experiments on adversarial watermarking that aim to deliver the same image quality as glaze with less computation and more resistance. We want to secure digital identity and copyrights. Watermarking is our initial approach.