{"ID":2826989,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17350","arxiv_id":"2512.17350","title":"Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection","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.","short_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 generat...","url_abs":"https://arxiv.org/abs/2512.17350","url_pdf":"https://arxiv.org/pdf/2512.17350v1","authors":"[\"Chenming Zhou\",\"Jiaan Wang\",\"Yu Li\",\"Lei Li\",\"Juan Cao\",\"Sheng Tang\"]","published":"2025-12-19T08:47:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\"]","has_code":false}