{"ID":2859332,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.05891","arxiv_id":"2510.05891","title":"$\\bf{D^3}$QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection","abstract":"The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete token prediction, exhibiting both marked improvements in image synthesis quality and unique characteristics in their vector-quantized representations. In this paper, we propose to leverage Discrete Distribution Discrepancy-aware Quantization Error (D$^3$QE) for autoregressive-generated image detection that exploits the distinctive patterns and the frequency distribution bias of the codebook existing in real and fake images. We introduce a discrete distribution discrepancy-aware transformer that integrates dynamic codebook frequency statistics into its attention mechanism, fusing semantic features and quantization error latent. To evaluate our method, we construct a comprehensive dataset termed ARForensics covering 7 mainstream visual AR models. Experiments demonstrate superior detection accuracy and strong generalization of D$^3$QE across different AR models, with robustness to real-world perturbations. Code is available at \\href{https://github.com/Zhangyr2022/D3QE}{https://github.com/Zhangyr2022/D3QE}.","short_abstract":"The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusion-based methods, AR models generate images through discrete token prediction, exhibiting both marked improvements in image synthesis qualit...","url_abs":"https://arxiv.org/abs/2510.05891","url_pdf":"https://arxiv.org/pdf/2510.05891v1","authors":"[\"Yanran Zhang\",\"Bingyao Yu\",\"Yu Zheng\",\"Wenzhao Zheng\",\"Yueqi Duan\",\"Lei Chen\",\"Jie Zhou\",\"Jiwen Lu\"]","published":"2025-10-07T13:02:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Transformer\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":608629,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859332,"paper_url":"https://arxiv.org/abs/2510.05891","paper_title":"$\\bf{D^3}$QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection","repo_url":"https://github.com/Zhangyr2022/D3QE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}