Saved in:
Bibliographic Details
Main Authors: Zhou, Chenming, Wang, Jiaan, Li, Yu, Li, Lei, Cao, Juan, Tang, Sheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17350
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908722119311360
author Zhou, Chenming
Wang, Jiaan
Li, Yu
Li, Lei
Cao, Juan
Tang, Sheng
author_facet Zhou, Chenming
Wang, Jiaan
Li, Yu
Li, Lei
Cao, Juan
Tang, Sheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
Zhou, Chenming
Wang, Jiaan
Li, Yu
Li, Lei
Cao, Juan
Tang, Sheng
Computer Vision and Pattern Recognition
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.
title Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.17350