2025/10/07 by Zhang, Yanran, Yu, Bingyao, Zheng, Yu +5
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2510.05891
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 (D3QE) 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 D3QE across different AR models, with robustness to real-world perturbations. Code is available at \hrefhttps://github.com/Zhangyr2022/D3QEhttps://github.com/Zhangyr2022/D3QE.