Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection

TL;DR

This paper proposes a pixel-level mapping pre-processing technique that disrupts semantic cues in images, enabling AI-generated image detectors to better generalize across different generative models by focusing on fundamental high-frequency artifacts.

Contribution

The introduction of a pixel-level mapping pre-processing step that enhances the cross-generator generalization of AI-generated image detectors.

Findings

Significantly improves detector performance on unseen generators

Disrupts semantic cues to focus on generative artifacts

Validates the approach across GAN and diffusion models

Abstract

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.