I wouldn’t be surprised if someone is working on that as a PhD thesis right now.
how are you going to write a thesis on writing a FLAC to disc and ripping it over and over?
By measuring how it does with real images vs generated ones to start. The goal would be to show a method to reliably detect ai images. Gotta prove that it works.
How would it detect, you would need the model and if you do you can already detect