Metraipolis › archive › dc_c2c00a1657cf

V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors — arXiv:2608.03008

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03008
License (as archived): CC0-1.0
Archived: 2026-10-31T12:18:25.391Z
SHA-256 of the archived text: c902a1115d5a264df98b5b6b373f67970287761ae6350bc9b944b9902ce4abb9
Stable URL of this page: https://metraipolis.com/documento/dc_c2c00a1657cf

How to cite

V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors — arXiv:2608.03008 — arXiv (en), https://arxiv.org/abs/2608.03008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2c00a1657cf (Metraipolis archive dc_c2c00a1657cf, sha256 c902a1115d5a264df98b5b6b373f67970287761ae6350bc9b944b9902ce4abb9)

BibTeX

@misc{dcc2c00a1657cf,
  title = {V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors — arXiv:2608.03008},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03008},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2c00a1657cf; sha256 c902a1115d5a264df98b5b6b373f67970287761ae6350bc9b944b9902ce4abb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on resource-intensive full-model retraining to steadily improve detection performance, we ask whether video forgery detection can also be achieved by uncovering and activating sparse forensic knowledge within the detector. We find that forgery-discriminative knowledge is not uniformly distributed across the full representation space, but is concentrated in a sparse set of functionally specialized neurons. Based on this insight, we propose a video forgery-intrinsic neuron discovery (V-FIND) framework. V-FIND first localizes critical layers that exhibit pronounced discrepancies between real and forged videos, and then identifies latent anchor neurons that consistently carry forgery-discriminative signals, organizing them into a compact forensic subspace. With the original backbone frozen and only a lightweight linear classifier trained, this subspace still delivers strong detection performance across multiple external benchmarks for generated videos. Further neuron intervention experiments provide direct evidence for the functional specificity of the discovered neurons. Overall, these results suggest that video forgery detectors contain sparse, extractable, and reusable forgery-discriminative knowledge, offering a new perspective on understanding and exploiting their intrinsic forensic capability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03008 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.976Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).