Degradation-Consistent Paired Training for Robust AI-Generated Image Detection 事件

Degradation-Consistent Paired Training for Robust AI-Generated Image Detection arXiv:2604.10102v2 Announce Type: replace Abstract: AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free, treat degradation robustness as a byproduct of data augmentation rather than an explicit training objective. In this work, we propo