CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915211430068224 |
|---|---|
| author | Cheng, Siyuan Lyu, Lingjuan Wang, Zhenting Zhang, Xiangyu Sehwag, Vikash |
| author_facet | Cheng, Siyuan Lyu, Lingjuan Wang, Zhenting Zhang, Xiangyu Sehwag, Vikash |
| contents | 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 at https://github.com/Megum1/Co-Spy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI Cheng, Siyuan Lyu, Lingjuan Wang, Zhenting Zhang, Xiangyu Sehwag, Vikash Computer Vision and Pattern Recognition 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 at https://github.com/Megum1/Co-Spy. |
| title | CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18286 |