FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
This addresses the issue of potential misuse of AI-generated images for researchers and practitioners in media forensics, though it is incremental as it builds on existing detection methods.
The paper tackles the problem of detecting images generated by diffusion models, which are hard to distinguish from real images, by proposing a method called FIRE that uses frequency-guided reconstruction error, achieving robust detection with generalization to unseen models and perturbations.
The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.