发表机构
Huazhong University of Science and Technology; Institute of Automation, Chinese Academy of Sciences; Jilin University; Tsinghua University（华中科技大学; 中国科学院自动化研究所; 吉林大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对AI生成图像检测器在现实世界通道传播后性能下降问题，提出GlobalForge框架，通过局部信息瓶颈和全局结构推理模块，基于退化对比结构损失联合训练，提升了检测器在多种基准上的性能。
AI 中文摘要
人工智能生成图像（AIGI）检测器在干净基准上有很高准确率，但图像经现实世界通道传播后性能大幅下降。研究发现其脆弱性源于过度拟合生成器在小空间邻域留下的局部伪像，易被常见传播退化破坏。为此提出GlobalForge框架，含局部信息瓶颈（LIB）和全局结构推理（GSR）模块，二者基于退化的对比结构损失联合训练以保持特征稳定。还引入RealDeg - Bench支持细粒度鲁棒性评估。GlobalForge在8个野外基准组上平均BAcc比之前最先进方法提高5.89%，在RealDeg - Bench的单退化和复合退化下均领先于代表性基线。
英文摘要
AI-generated image (AIGI) detectors achieve strong accuracy on clean benchmarks, but their performance drops sharply after images are propagated through real-world channels. We trace this fragility to what these detectors actually learn: they overfit to local artifacts left by generators in small spatial neighborhoods, which are easily destroyed by common propagation degradations such as JPEG compression and blur. Instead, we shift the discriminative cue from fragile local artifacts to more robust global structure. Building on this, we propose GlobalForge, a framework with two complementary modules. The Local Information Bottleneck (LIB) suppresses local components to block shortcut learning, while the Global Structural Reasoning (GSR) module forces every token to gather evidence from distant regions. Both modules are trained jointly under a contrastive structural loss based on degradation that keeps the resulting features stable under degradation. To support fine-grained robustness evaluation, we further introduce RealDeg-Bench, covering 7 common degradation operators and multi-step compound chains. GlobalForge improves average BAcc on 8 in-the-wild benchmark groups by $\mathbf{5.89\%}$ over the previous state-of-the-art, and is clearly ahead of representative baselines on RealDeg-Bench under both single and compound degradations. Code is available at https://anonymous.4open.science/r/GlobalForge-BE0F/.
