5 papers
Riemannian-Geometric Fingerprints of Generative Models
Hae Jin Song, Laurent Itti
Recent breakthroughs and rapid integration of generative models (GMs) have sparked interest in the problem of model attribution and their fingerprints. For instance, service provid…
MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning
Seungbeom Hu, ChanJun Park, Andrew Ferraiuolo +4
Determining the optimal size of a neural network is critical, as it directly impacts runtime performance and memory usage. Pruning is a well-established model compression technique…
Application of Disentanglement to Map Registration Problem
Hae Jin Song, Patrycja Krawczuk, Po-Hsuan Huang
Geospatial data come from various sources, such as satellites, aircraft, and LiDAR. The variability of the source is not limited to the types of data acquisition techniques, as we…
ManiFPT: Defining and Analyzing Fingerprints of Generative Models
Hae Jin Song, Mahyar Khayatkhoei, Wael AbdAlmageed
Recent works have shown that generative models leave traces of their underlying generative process on the generated samples, broadly referred to as fingerprints of a generative mod…
Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints
Hae Jin Song, Wael AbdAlmageed
With recent progress in deep generative models, the problem of identifying synthetic data and comparing their underlying generative processes has become an imperative task for vari…