2D-FACT: Dual-Domain Fake Image Detection Against Text-to-Image Generative Models
Published in MIT Undergraduate Research Technology Conference (URTC), 2023
Recommended citation: E. Ji, B. Dong, B. Samanthula, N. Zhou. "2D-FACT: Dual-Domain Fake Image Detection Against Text-to-Image Generative Models". MIT Undergraduate Research Technology Conference (URTC 2023).
Recent developments in generative artificial intelligence are bringing great concerns for privacy, security and misinformation. Our work focuses on the detection of fake images generated by text-to-image models. We propose a dualdomain CNN-based classifier that utilizes image features in both the spatial and frequency domain. Through an extensive set of experiments, we demonstrate that the frequency domain features facilitate high accuracy, zero-transfer learning between different generative models, and faster convergence. To our best knowledge, this is the first effective detector against generative models that are finetuned for a specific subject.