Search papers, labs, and topics across Lattice.
This paper introduces GlobalForge, a novel framework designed to enhance the robustness of AI-generated image detectors against real-world degradation. By addressing the overfitting to local artifacts, GlobalForge employs a Local Information Bottleneck to minimize shortcut learning and a Global Structural Reasoning module to ensure comprehensive evidence gathering from distant regions. The approach yields a significant improvement of 5.89% in average balanced accuracy on various in-the-wild benchmark groups compared to existing state-of-the-art methods.
GlobalForge shifts the focus from fragile local artifacts to robust global structures, achieving a 5.89% accuracy boost in detecting AI-generated images under real-world conditions.
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/.
