Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
This addresses the generalization issue in AI-generated image detection, which is crucial for security and media integrity, though it is incremental as it builds on existing detectors with a novel pre-processing step.
The paper tackles the problem of AI-generated image detectors failing to generalize to unseen generative models by introducing a pixel-level mapping pre-processing step that disrupts pixel value distributions to break semantic shortcuts. The result shows a significant boost in cross-generator performance for state-of-the-art detectors, as verified through experiments on GAN and diffusion-based generators.
The rapid evolution of generative technologies necessitates reliable methods for detecting AI-generated images. A critical limitation of current detectors is their failure to generalize to images from unseen generative models, as they often overfit to source-specific semantic cues rather than learning universal generative artifacts. To overcome this, we introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images and break the fragile, non-essential semantic patterns that detectors commonly exploit as shortcuts. This forces the detector to focus on more fundamental and generalizable high-frequency traces inherent to the image generation process. Through comprehensive experiments on GAN and diffusion-based generators, we show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors. Extensive analysis further verifies our hypothesis that the disruption of semantic cues is the key to generalization.