AdaParse: Personalized Fingerprinting for Visual Generative Model Reverse Engineering

Summary

AdaParse is a hyperparameter-specialized adaptive fingerprinting framework for model reverse engineering, which predicts hyperparameters of generative models from AI-generated images. It personalizes fingerprint estimation networks per input image using two-branch hypernetworks and a Broadcasted Fusion module. Experiments on a large public dataset covering 123 generative models show it outperforms previous state-of-the-art methods.