フレーム精度を超えて：TransformerベースDeepfake鑑定における動画レベル安定性の分析
Beyond Frame-Level Accuracy: Analyzing Video-Level Stability in Transformer-Based Deepfake Forensics
CNNとViTを同一条件で比較し、CNNはフレーム単位では競争力があるが動画レベル集約で性能が低下する一方、ViT-B/16は動画レベルで安定した精度を示すことを明らかにした。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Syed Azmul Hasan, Mowmita Pervin Hera, Afroza Lona Mim, M M Jihad Hossain, Hazrat Ali, Mohammad Farhad Bulbul
分類: cs.CV, cs.AI, cs.LG
原文アブストラクト
Deepfake videos generated by advanced generative models pose serious threats to digital security, misinformation control, and media forensics. Although numerous detection methods have been proposed, their reported performances are often based on heterogeneous preprocessing pipelines, inconsistent data splits, and model-specific training protocols, hindering fair architectural comparison. This work presents a controlled and reproducible comparative study of convolutional neural networks (ResNet-18 and EfficientNet-B0) and a transformer-based architecture (ViT-B/16) within a unified, face-centric deepfake detection framework. All models are trained using identical preprocessing, augmentation, optimization settings, and data splits on Celeb-DF v2 and FaceForensics++, and results are validated across three independent random seeds with bootstrapped confidence intervals. Experimental results show that while CNN-based models perform competitively at the frame level, their performance degrades after video-level aggregation. In contrast, ViT-B/16 demonstrates more stable video-level performance, achieving 92.8\% [95\% CI: 91.7--94.0] video-level accuracy and an AUC of 0.950 [95\% CI: 0.934--0.964] on Celeb-DF v2 (3-seed bootstrapped). Cross-dataset evaluation across the same three random seeds reveals a large, asymmetric generalization gap (AUC 0.79 FF++$\rightarrow$Celeb-DF vs. 0.64 Celeb-DF$\rightarrow$FF++), indicating that in-domain video-level stability does not transfer to unseen manipulation domains. These findings indicate that global self-attention improves robustness and video-level stability for deepfake detection within a given data domain, while highlighting the need for further work on cross-domain generalization.