发表机构
California State University, Northridge（加州州立大学北岭分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出AdaGate-DF自适应门控深度伪造检测框架，通过双多出口系统节省计算，在Celeb-DF和FaceForensics++数据集上实现性能与效率的平衡，优于部分对比模型。
AI 中文摘要
深度伪造检测模型通常依赖高质量输入、固定推理路径及计算成本高昂的架构，限制了其在低分辨率与资源受限场景的应用。本文提出AdaGate-DF，一种自适应门控深度伪造检测框架，利用图像质量线索通过双多出口系统路由样本，使高质量图像可提前退出以节省计算。在多配置下于两个基准数据集Celeb-DF和FaceForensics++上，将AdaGate-DF与MaD-CoRN、DefakeHop++及ShuffleNetV2对比，测试其对图像分辨率的依赖性、训练与推理效率。在Celeb-DF上，AdaGate-DF的AUC达0.9370，在保持低推理延迟的同时优于MaD-CoRN和DefakeHop++；分辨率测试显示，随输入分辨率提升性能持续改善，384×384时AUC达0.9708。FaceForensics++的结果表明，AdaGate-DF在类别不平衡下仍有效，与对比模型结果相当。总体而言，AdaGate-DF在可变质量深度伪造检测的性能、不确定性感知预测与计算效率间实现了实用平衡。
英文摘要
Deepfake detection models often rely on high-quality inputs, fixed inference paths, and computationally expensive architectures, limiting their use in low-resolution and resource-constrained settings. This paper proposes AdaGate-DF, an adaptive gated deepfake detection framework that uses image-quality cues to route samples through a dual multi-exit system so high-quality images can exit earlier and save compute. We evaluated AdaGate-DF against MaD-CoRN, DefakeHop++, and ShuffleNetV2 on two benchmark datasets (Celeb-DF and FaceForensics++) under multiple configurations to test image resolution dependence and training and inference efficiency. On Celeb-DF, AdaGate-DF achieves an AUC of 0.9370, outperforming MaD-CoRN and DefakeHop++ while maintaining a low inference latency. Resolution-based testing shows consistent improvement as input resolution increases, reaching an AUC of 0.9708 at 384 by 384. The FaceForensics++ results highlight that AdaGate-DF remains effective under class imbalance, following competitive results with evaluated models. Overall, AdaGate-DF demonstrated a practical balance between detection performance, uncertainty-aware prediction, and computational efficiency for variable-quality deepfake detection.
