Re:Ownership of AI-Generated Code Hotly Disputed
by godelski on Friday December 30, 2022 @01:06PM
(#34187824)
So there a few ways this can actually be done with different levels of accuracy/precision. But it is going to be complicated no matter what.
The easy thing to do is to compare outputs to inputs. This isn't technically hard (i.e. cosine similarity) but it is computationally difficult (i.e. cosine similarity of output to entire input). This would give us some weightings that show similarity. But this doesn't really tell us attribution, rather more a correlation. These are statistical models so there's reason to believe that this is okay.
Then there's inversion. This is processing data backwards through the model. This has different complexities compared to what type of model you're working with. GANs aren't great, diffusions are okay, normalizing flows are trivial (but good luck generating good images from NFs). If we can invert the model it is much easier to investigate and probe for contribution by looking at the distance of the latent generative variable to the location of the latent trained data. Basically you're looking at how different information is contributing to the overall output. This can also be done at every level in the network. Obviously this gets both technically challenging as well as computationally.
Another method would be using dataset reconstruction (this is outside my wheelhouse fwiw). This is where you try to recover the dataset from the final trained network. This too is complicated but there's plenty of papers showing progress in this space (lots of interest from privacy groups).
(TLDR-ish) There's other methods too. But basically what is being said is that there are ways to denote what and how much the training data contributed to the output of the model wherein we can then measure how similar the output is to the inputs (i.e. copying).
The easy thing to do is to compare outputs to inputs. This isn't technically hard (i.e. cosine similarity) but it is computationally difficult (i.e. cosine similarity of output to entire input). This would give us some weightings that show similarity. But this doesn't really tell us attribution, rather more a correlation. These are statistical models so there's reason to believe that this is okay.
Then there's inversion. This is processing data backwards through the model. This has different complexities compared to what type of model you're working with. GANs aren't great, diffusions are okay, normalizing flows are trivial (but good luck generating good images from NFs). If we can invert the model it is much easier to investigate and probe for contribution by looking at the distance of the latent generative variable to the location of the latent trained data. Basically you're looking at how different information is contributing to the overall output. This can also be done at every level in the network. Obviously this gets both technically challenging as well as computationally.
Another method would be using dataset reconstruction (this is outside my wheelhouse fwiw). This is where you try to recover the dataset from the final trained network. This too is complicated but there's plenty of papers showing progress in this space (lots of interest from privacy groups).
(TLDR-ish) There's other methods too. But basically what is being said is that there are ways to denote what and how much the training data contributed to the output of the model wherein we can then measure how similar the output is to the inputs (i.e. copying).