3 papers
cs.CV2025
A Bias-Free Training Paradigm for More General AI-generated Image Detection
Fabrizio Guillaro, Giada Zingarini, Ben Usman +3
Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is lar…
cs.CV2024
FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion
George Cazenavette, Avneesh Sud, Thomas Leung +1
Due to the high potential for abuse of GenAI systems, the task of detecting synthetic images has recently become of great interest to the research community. Unfortunately, existin…
cs.LG2024
Towards Practical Non-Adversarial Distribution Matching
Ziyu Gong, Ben Usman, Han Zhao +1
Distribution matching can be used to learn invariant representations with applications in fairness and robustness. Most prior works resort to adversarial matching methods but the r…