Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection

• URL: http://arxiv.org/abs/2607.21776v1
• Date: Thu, 23 Jul 2026 19:47:15 GMT
• Title: Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection
• Abstract summary: Talking-face (TF) deep-swap generation synthesizes photore- alistic facial video from a static source image and an au-fake signal, producing forgeries that current image-based detectors consistently fail to identify.<n>We propose a detection framework that extracts per-video r wave forms via RhythmFormer and trains a suite of lightweight classifiers to distinguish real signals.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries that current image-based detectors consistently fail to identify. Unlike face-swap ma- nipulation, TF synthesis has no underlying real video from which to inherit physiological characteristics, making re- mote photoplethysmography (rPPG) a uniquely motivated detection modality for this forgery category. We propose a detection framework that extracts per-video rPPG wave- forms via RhythmFormer and trains a suite of lightweight classifiers to distinguish real from synthesized physiologi- cal signals. Evaluated on the TF subset of Celeb-DF++ un- der a strict subject-independent protocol, where test identi- ties are completely separated from training identities, our 1D ResNet achieves an AUC of 0.806 and EER of 27.8%, placing it within 2.4 points of the best published general- purpose detector (Effort, ICML 2025) while operating ex- clusively on the physiological channel. We document a con- trolled reproduction study of DeepFakesON-Phys, the rep- resentative prior rPPG detector, demonstrating degrada- tion from AUC 0.999 on legacy face-swap data to 0.622 on the TF subset of Celeb-DF++. We further show that detec- tion difficulty is strongly method-dependent: AUC ranges from 0.985 (Real3DPortrait) to 0.690 (IP-LAP) across the seven TF generators, with the ranking remaining perfectly stable across all evaluation protocols. This spread reflects an interpretable physiological property of each generator rather than evaluation noise, and constitutes the primary theoretical contribution of the work.

Related papers

• Beyond Ambiguous Visual Cues: Studying Physiological Disruptions and Cross-Modal Inconsistencies in Deepfake Videos [7.77578121448493]
  Current detectors underexplore the cross-level relationship between facial features and physiological dynamics, often relying on late fusion or r features alone.<n>We propose a bidirectional co-attention fusion detector that captures the cross-level dependencies between pulse dynamics and facial motion to learn a robust, joint authenticity representation.
  arXiv  Detail & Related papers  (2026-09-11T10:12:48Z)
• Label-Free Parkinson's Disease Screening from Face and Voice through Mechanistic Interpretability [4.241413288920499]
  Parkinson's disease (PD) is the second most common neurodegenerative disorder.<n>We propose a label-free face-plus-voice PD screen built entirely on frozen pretrained encoders.<n>We show that a synthetic-degradation CAA detector works when the cosine similarity between the synthetic and real disease directions exceeds zero.
  arXiv  Detail & Related papers  (2026-08-10T00:43:57Z)
• Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection [9.42962723864652]
  This paper describes the participation of team "Go To Germany" in the ImageCLEF 2026 Deepfake Detection and Generation Task.<n>For the image generation task, we employ FLUX.1-dev with PuLID for identity-preserving face synthesis.<n>For the image detection task, we combine two complementary detectors - SigLIP+DINOv2 for AI-generated images and GenD-DINOv3 for face manipulations.
  arXiv  Detail & Related papers  (2026-07-28T15:19:16Z)
• Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration [0.0]
  Consumer face camera remote photoplethys hallucination (r) enables passive cardiovascular monitoring.<n>But whether single-cycle waveform morphology encoding arterial stiffness is recoverable from this measurement has not been characterised.<n>We evaluated 16 encoder architectures spanning six families on 153 subjects across three datasets.
  arXiv  Detail & Related papers  (2026-06-02T15:50:07Z)
• Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis [4.672369796753925]
  Existing foundation models rely on continuous latent spaces, which frequently suffer from severe modality entanglement.<n>We propose Compact Latent Translation (CLMT), a highly parameter-efficient (0.09B) unified framework that bridges these gaps.<n>By learning a universal discrete language for biological signals with a fraction of the computational footprint, our approach sets a new trajectory for edge-deployable, multi-fidelity medical foundation models.
  arXiv  Detail & Related papers  (2026-05-13T09:31:36Z)
• Physiology as Language: Translating Respiration to Sleep EEG [43.02603129452492]
  This paper introduces a novel cross-physiology translation task: synthesizing sleep electroencephalography (EEG) from respiration signals.<n>We propose a waveform-conditional generative framework that preserves fine-grained respiratory dynamics while constraining the EEG target space through discrete tokenization.<n>Trained on over 28,000 individuals, our model achieves a 7% Mean Absolute Error in EEG spectrogram reconstruction.
  arXiv  Detail & Related papers  (2026-01-31T05:44:45Z)
• EMPalm: Exfiltrating Palm Biometric Data via Electromagnetic Side-Channels [54.460942487872416]
  EM emissions leak palm biometric information.<n> EMPalm is an attack framework that covertly recovers both palmprint and palmvein images from eavesdropped EM signals.
  arXiv  Detail & Related papers  (2025-10-08T20:50:19Z)
• AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification [0.0]
  We propose AudioFuse, an architecture that learns from both complementary representations to classify PCGs.<n>On the PhysioNet 2016 dataset, AudioFuse achieves a state-of-the-art competitive ROC-AUC of 0.8608 when trained from scratch.
  arXiv  Detail & Related papers  (2025-09-27T18:52:50Z)
• PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution [60.970656010712275]
  We propose a combination of diffusion-based generation (PanoDiff) and Super-Resolution (SR) for generating synthetic dental panoramic radiographs (PRs)<n>The former generates a low-resolution (LR) seed of a PR which is then processed by the SR model to yield a high-resolution (HR) PR of size 1024 X 512.<n>For SR, we propose a state-of-the-art transformer that learns local-global relationships, resulting in sharper edges and textures.
  arXiv  Detail & Related papers  (2025-07-12T09:52:10Z)
• HistoART: Histopathology Artifact Detection and Reporting Tool [37.31105955164019]
  Whole Slide Imaging (WSI) is widely used to digitize tissue specimens for detailed, high-resolution examination.<n>WSI remains vulnerable to artifacts introduced during slide preparation and scanning.<n>We propose and compare three robust artifact detection approaches for WSIs.
  arXiv  Detail & Related papers  (2025-06-23T17:22:19Z)
• Facial Kinship Verification from remote photoplethysmography [8.212664345436092]
  Kinship Verification (FKV) aims at automatically determining whether two subjects have a kinship relation based on human faces. Traditional FKV faces challenges as it is vulnerable to spoof attacks and raises privacy issues. In this paper, we explore for the first time the FKV with vital bio-signals, focusing on remote Photoplethys reflection.
  arXiv  Detail & Related papers  (2023-09-14T19:33:11Z)
• Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues [81.15465149555864]
  We establish the first joint face spoofing and detection benchmark using both visual appearance and physiological r cues. To enhance the r periodicity discrimination, we design a two-branch physiological network using both facial powerful rtemporal signal map and its continuous wavelet transformed counterpart as inputs.
  arXiv  Detail & Related papers  (2022-08-10T15:41:48Z)
• Identifying Rhythmic Patterns for Face Forgery Detection and Categorization [46.21354355137544]
  We propose a framework for face forgery detection and categorization consisting of: 1) a Spatial-Temporal Filtering Network (STFNet) for PPG signals, and 2) a Spatial-Temporal Interaction Network (STINet) for constraint and interaction of PPG signals. With insight into the generation of forgery methods, we further propose intra-source and inter-source blending to boost the performance of the framework.
  arXiv  Detail & Related papers  (2022-07-04T04:57:06Z)
• Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling [121.50704279659253]
  We propose a cross-verified feature disentangling strategy to disentangle the physiological features with non-physiological representations. We then use the distilled physiological features for robust multi-task physiological measurements. The disentangled features are finally used for the joint prediction of multiple physiological signals like average HR values and r signals.
  arXiv  Detail & Related papers  (2020-07-16T09:39:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.