Efficient Zero-Shot AI-Generated Image Detection
This addresses the challenge of accurate detection of realistic AI-generated images for applications like content moderation, though it is incremental as it builds on existing training-free approaches.
The paper tackles the problem of detecting AI-generated images by proposing a training-free method that measures representation sensitivity to structured frequency perturbations, achieving a 10% AUC improvement on the OpenFake benchmark and one to two orders of magnitude faster inference than most training-free detectors.
The rapid progress of text-to-image models has made AI-generated images increasingly realistic, posing significant challenges for accurate detection of generated content. While training-based detectors often suffer from limited generalization to unseen images, training-free approaches offer better robustness, yet struggle to capture subtle discrepancies between real and synthetic images. In this work, we propose a training-free AI-generated image detection method that measures representation sensitivity to structured frequency perturbations, enabling detection of minute manipulations. The proposed method is computationally lightweight, as perturbation generation requires only a single Fourier transform for an input image. As a result, it achieves one to two orders of magnitude faster inference than most training-free detectors.Extensive experiments on challenging benchmarks demonstrate the efficacy of our method over state-of-the-art (SoTA). In particular, on OpenFake benchmark, our method improves AUC by nearly $10\%$ compared to SoTA, while maintaining substantially lower computational cost.