这篇论文为AI生成图像检测开辟了全新维度——从社交凝视一致性入手，解决了传统低级伪影检测在人物交互场景中的失效问题。做图像取证、内容安全或生成模型评估的团队值得关注，其跨架构泛化能力意味着可以直接应用于现有检测系统。
该论文提出了一种名为“社交凝视一致性”的高层语义线索，用于检测AI生成的图像。与传统的基于低级伪影（如像素指纹、频率异常）的方法不同，该线索关注交互个体之间视线方向、头眼对齐和瞳孔位置的相互一致性。研究者通过构建受控诊断数据集、采用块组合字幕监督方法，并在多个架构上验证，证明该线索能有效提升检测性能，例如在FakeVLM模型上，COCOAI Interaction子集的平衡准确率从67.8%提升至71.5%。该方法在真实和伪造类别的召回率上同时提升，避免了“全预测为假”的偏差，且训练于单一修复模型（FLUX.1-Fill）后能泛化到多生成器场景。
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partial-edit settings where the manipulated region is small and surrounded by photometrically authentic content. We introduce Social Gaze Consistency, a high-level semantic cue defined as the mutual coherence of gaze direction, head-eye alignment, and pupil placement between interacting individuals, and show that it constitutes a previously underutilized detection axis orthogonal to existing low-level paradigms. We instantiate this insight through three coupled mechanisms: (i) a controlled diagnostic dataset with region-specific perturbations of gaze-consistent imagery, where strict pair-level grouping forecloses generator-fingerprint memorization as an optimization-time shortcut rather than relying on augmentation; (ii) Block-Compositional Caption Supervision, which holds a single 5-block reasoning skeleton invariant across 1,250 macro-combined captions, decoupling reasoning consistency from surface diversity; (iii) Cross-architecture validation showing the same supervision improves a vision-language backbone (FakeVLM) by +3.7 pp on the COCOAI Interaction subset (balanced accuracy 67.8 -> 71.5) and +1.3 pp on the COCOAI Person subset (83.0 -> 84.3), with consistent gains on a vision-only backbone (Effort), evidencing a backbone-agnostic cue. Real- and fake-class recalls rise simultaneously, ruling out a "predict-all-fake" artifact. A four-step mechanistic account - paired-edit shortcut blocking, hard-to-easy difficulty transfer, CLIP prior preservation, and diffusion-family shared spectral weakness in periocular structure - explains why training on a single inpainter (FLUX.1-Fill) transfers to multi-generator suites. We will release the code upon acceptance to facilitate reproducibility.