Enhancing Frequency Forgery Clues for Diffusion-Generated Image Detection
This addresses the need for reliable detection of AI-generated images to prevent misuse, representing an incremental improvement in domain-specific detection methods.
The paper tackled the problem of detecting images generated by diffusion models, which can be used maliciously, by proposing a method that enhances frequency forgery clues across all frequency bands, resulting in outperforming state-of-the-art detectors with superior generalization and robustness in experiments.
Diffusion models have achieved remarkable success in image synthesis, but the generated high-quality images raise concerns about potential malicious use. Existing detectors often struggle to capture discriminative clues across different models and settings, limiting their generalization to unseen diffusion models and robustness to various perturbations. To address this issue, we observe that diffusion-generated images exhibit progressively larger differences from natural real images across low- to high-frequency bands. Based on this insight, we propose a simple yet effective representation by enhancing the Frequency Forgery Clue (F^2C) across all frequency bands. Specifically, we introduce a frequency-selective function which serves as a weighted filter to the Fourier spectrum, suppressing less discriminative bands while enhancing more informative ones. This approach, grounded in a comprehensive analysis of frequency-based differences between natural real and diffusion-generated images, enables general detection of images from unseen diffusion models and provides robust resilience to various perturbations. Extensive experiments on various diffusion-generated image datasets demonstrate that our method outperforms state-of-the-art detectors with superior generalization and robustness.