# Physics-Aware Deepfake Detection via Distance-Speech Consistency

arXiv: https://arxiv.org/abs/2610.18485 · HTML: https://mlsanity.com/paper/2610.18485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Detecting Deepfakes with Self-Blended Images](https://mlsanity.com/paper/2204.08376/) (2022)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset](https://mlsanity.com/paper/2311.15308/) (2023)
- [D3: Scaling Up Deepfake Detection by Learning from Discrepancy](https://mlsanity.com/paper/2404.04584/) (2024)
- [Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024](https://mlsanity.com/paper/2503.02857/) (2025)
- [Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization](https://mlsanity.com/paper/2305.01979/) (2023)
- [D3: Training-Free AI-Generated Video Detection Using Second-Order Features](https://mlsanity.com/paper/2508.00701/) (2025)
- [Revisiting Over-Smoothness in Text to Speech](https://mlsanity.com/paper/2202.13066/) (2022)
- [SAM Audio: Segment Anything in Audio](https://mlsanity.com/paper/2512.18099/) (2025)
- [Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection](https://mlsanity.com/paper/2401.05746/) (2024)
- [Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2501.01184/) (2025)
- [Distance-Based Sound Separation](https://mlsanity.com/paper/2207.00562/) (2022)
- [Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies](https://mlsanity.com/paper/2408.06753/) (2024)
- [SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection](https://mlsanity.com/paper/2508.09913/) (2025)
- [AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization](https://mlsanity.com/paper/2511.18993/) (2025)
- [Zero-Shot Mono-to-Binaural Speech Synthesis](https://mlsanity.com/paper/2412.08356/) (2024)

## Abstract (arXiv)

Recent progress in generative models has made talking-head deepfakes highly realistic and easy to create, jeopardizing public trust. However, most audio-visual deepfake detectors rely on lip-speech synchronization and are designed for static, frontal videos, limiting their reliability in dynamic, in-the-wild recordings where the speaker moves and lip cues are degraded or missing. As an alternative, we propose a physics-aware detector for dynamic speaking videos that leverages an acoustic constraint: in real recordings, speech energy varies predictably with speaker-to-camera distance, whereas deepfake generation can break this coupling. Our method combines distance estimates from video with distance-dependent acoustic measures from speech to detect deepfakes. Experiments on in-the-wild benchmarks show that the proposed physical cue is effective in dynamic scenarios, and that it complements lip-sync-based detectors, with a simple ensemble achieving consistent gains across datasets. Codes are available at https://byulharang.github.io/PADD/.