CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
Abstract
With the rapid advancement of generative AI, it is now pos-
sible to synthesize high-quality images in a few seconds.
Despite the power of these technologies, they raise signif-
icant concerns regarding misuse. Current efforts to dis-
tinguish between real and AI-generated images may lack
generalization, being effective for only certain types of gen-
erative 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-SPYBENCH, 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 eval-
uation 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%.
Authors
- Siyuan Cheng
- Lingjuan Lyu
- Zhenting Wang
- Xiangyu Zhang
- Vikash Sehwag
Venue
CVPR-25
Date
2025