Metraipolis › archive › dc_ddfbf82c78b5
AI or Real: Detecting Partially Altered Videos Under Resource-Constrained Environments — arXiv:2609.20263
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20263
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:51:01.657Z
- SHA-256 of the archived text
31827f075a143f05356f375c80346d545ca5c6a7d40d34b22b290f1071b631c6- Stable URL of this page
https://metraipolis.com/documento/dc_ddfbf82c78b5
How to cite
AI or Real: Detecting Partially Altered Videos Under Resource-Constrained Environments — arXiv:2609.20263 — arXiv (en), https://arxiv.org/abs/2609.20263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ddfbf82c78b5 (Metraipolis archive dc_ddfbf82c78b5, sha256 31827f075a143f05356f375c80346d545ca5c6a7d40d34b22b290f1071b631c6)
BibTeX
@misc{dcddfbf82c78b5,
title = {AI or Real: Detecting Partially Altered Videos Under Resource-Constrained Environments — arXiv:2609.20263},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20263},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ddfbf82c78b5; sha256 31827f075a143f05356f375c80346d545ca5c6a7d40d34b22b290f1071b631c6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The proliferation of generative video models has shifted the practical detection threat from fully fabricated clips to partially manipulated footages. Although modern detectors achieve strong accuracy using foundation backbones of 400M+ parameters, their resource footprint precludes edge deployment. In this paper, we present a lightweight full-frame detector for partially manipulated AI-generated video, designed for deployment on edge hardware without face-detection preprocessing. The system distills a DINOv2-Base teacher into a frozen MobileNetV3-Small student through a pipeline that combines temperature-annealed soft-label transfer, attention-diversity regularization, frame-level supervision, and a residual feature adapter that conditions ImageNet features for artifact detection. We additionally target two failure modes specific to the partial-manipulation regime: false positives on legitimate scene cuts, addressed through within-video temporal hard negatives; and threshold-level miscalibration on the dominant pure-real class, addressed through calibration-aware sampling. Evaluation on a 55,393-sample spliced test set across fake-frame ratios from 6.2% to 31.2% demonstrates the student model closing 58% of the gap to the DINOv2-Base teacher (AUC 0.766) while running at 3.65 ms per 16-frame clip on RTX A4000 with a 150.4 MB checkpoint compatible with edge-device memory and latency budgets. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-18 in cs.DC). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.20263 — 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 2026-10-10T03:24:19.945Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).