With the rapid advancement of generative AI, it is now possible to synthesize high-quality images in a few seconds. Despite the power of these technologies, they raise significant concerns regarding misuse. Current efforts to distinguish between real and AI-generated images may lack generalization, being effective for only certain types of generative models and susceptible to post-processing techniques like JPEG compression. To overcome these limitations, we propose a novel framework, Co-Spy, that first enhances existing semantic features (e.g., the number of fingers in a hand) and artifact features (e.g., pixel value differences), and then adaptively integrates them to achieve more general and robust synthetic image detection. Additionally, we create Co-Spy-Bench, a comprehensive dataset comprising 5 real image datasets and 22 state-of-the-art generative models, including the latest models like FLUX. We also collect 50k synthetic images in the wild from the Internet to enable evaluation in a more practical setting. Our extensive evaluations demonstrate that our detector outperforms existing methods under identical training conditions, achieving an average accuracy improvement of approximately 11% to 34%. The code is available atthis https URL.
View on arXiv@article{cheng2025_2503.18286,
title={ CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI },
author={ Siyuan Cheng and Lingjuan Lyu and Zhenting Wang and Xiangyu Zhang and Vikash Sehwag },
journal={arXiv preprint arXiv:2503.18286},
year={ 2025 }
}