{
  "id": 6714,
  "url": "https://arxiv.org/abs/2603.25140v1",
  "title": "SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment",
  "summary": "Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving",
  "authors": "Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment,misinformation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-26T08:01:35.000Z",
  "fetched_at": "2026-07-14T16:32:41.667Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6714",
  "original_url": "https://arxiv.org/abs/2603.25140v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}