脈拍か由来か?rPPGベースのディープフェイク検出器が学ぶもの
Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn
rPPGを用いたディープフェイク検出器が実際には生理信号ではなく高周波の生成アーティファクトや動画ソースを捉えていることを実験的に示した論文。
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: Othmane Harraq, Tamer Aldwairi
分類: cs.CV, cs.CR, cs.LG
原文アブストラクト
Remote photoplethysmography (rPPG) has been proposed as a physiological cue for deepfake detection, based on the premise that synthesized faces lack a genuine cardiac signal. We examine what rPPG-style detectors learn on Celeb-DF++ (22 forgery methods) and FaceForensics++ (FF++), using one identically sampled window per real and fake video. On talking-face forgeries, simple chrominance traces reach an AUC of 0.998, exceeding a dedicated rPPG extractor (0.87). Controlled experiments indicate that this signal is not physiological in origin. On fully synthesized forgeries, it is equally discriminative when extracted from background regions or from full frames without face detection, and it is concentrated above the 0.7 to 4 Hz heart-rate band. It is largely removed by shuffling frame order but persists after normalizing resolution, frame rate and encoding, and an independent reimplementation reproduces these findings. Removing high-frequency content makes most synthesized videos appear real, adding it makes real videos appear fake, and injecting a synthetic pulse has little effect. In controlled self-reenactment experiments with two generators, animating a face from a single frame introduces the same high-frequency signal, whereas reconstructing each frame from its own source does not. Face-based chrominance detectors trained on Celeb-DF++ classify over 99% of real FF++ videos as fake, indicating that they largely encode video source rather than manipulation, and a CLIP-based detector exhibits the same behavior. A frozen CLIP backbone matches or exceeds fusions of CLIP with rPPG and frequency features. Finally, we show that the official Celeb-DF and Celeb-DF++ splits share identities and source-video content between training and test, and that custom protocols reusing test videos and identities in training inflate weaker detectors by up to 0.30 AUC.
関連論文
- MoSTE:動画ディープフェイク検出のための時空間エキスパート混合ディープフェイク検出
- Spectra: マルチスケール暗黙分解によるディープフェイク検出ディープフェイク検出
- RoboFake:ディープフェイク検出器はヒューマノイド顔ロボットに対応できるか?ディープフェイク検出
- MSUチームによる説明可能なディープフェイク検出チャレンジ2026への挑戦:根拠あるアーティファクト証拠に基づく検出ディープフェイク検出
- MOTIF: 3DMM係数を超えた特定人物向けディープフェイク検出ディープフェイク検出
- 明示的なフォレンジック特徴と時間モデリングによる動画ディープフェイクの解釈可能な検出ディープフェイク検出