Context and Transcripts Improve Detection of Deepfake Audios of Public Figures

Documenti analoghi

• Perturbed Public Voices (P$^{2}$V): A Dataset for Robust Audio Deepfake Detection
  di: Gao, Chongyang, et al.
  Pubblicazione: (2025)
• Human-AI Ensembles Improve Deepfake Detection in Low-to-Medium Quality Videos
  di: Postiglione, Marco, et al.
  Pubblicazione: (2026)
• DEMON: Diffusion Engine for Musical Orchestrated Noise
  di: Fosdick, Ryan
  Pubblicazione: (2026)
• Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification
  di: Salvi, Davide, et al.
  Pubblicazione: (2025)
• ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection
  di: Chou, Benjamin, et al.
  Pubblicazione: (2026)