@article{jdrasiak2025deep,
  title = {Deep Network Representations as Reliable Indicators of Synthetic Content in Audiovisual and Clinical Contexts},
  author = {Karol JĘDRASIAK and Julia BIJOCH},
  year = 2025,
  url = {https://ibimapublishing.com/p-articles/46AI/2025/4638225/},
  journal = {Communications of International Proceedings},
  volume = 2025 (34),
  doi = doi.org/10.5171/2025.4638225,
  abstract = {This study introduces an interpretable framework for detecting synthetic audiovisual content using deep neural representations, applied to the DeepFake RealWorld (DFRW) dataset (46 371 clips; 77% with audio). Visual, acoustic, and cross-modal embeddings from ResNet, Vision Transformer, SlowFast, Wav2Vec2, and ECAPA-TDNN were evaluated with frequency-based metrics (Δp ≥ 0.15, PR ≥ 1.5). The strongest indicators were facial embedding variance (Δp = 0.29, PR = 3.4), Mahalanobis distance (Δp = 0.25), and audiovisual coherence (Δp = 0.23), all stable within 15% under compression and re-capture. In teledentistry and telemedicine, such explainable AI markers enhance authenticity verification of digital evidence and strengthen medico-legal reliability.},
  keywords = {Deepfake detection; deep neural representations; multimodal coherence; audiovisual forensics; explainable AI; telemedicine; teledentistry; data integrity},
  note = Article ID: 4638225
}