Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Trapeznikov, Kirill, Mancino-Ball, Gabriel, Li, Jonathan, Cummer, Paul, Aslam, Jai, Vahdati, Danial Samadi, Nguyen, Tai, Stamm, Matthew C., Bautista, Peter, Davinroy, Michael, Cassani, Laura, Crisman, Jill
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909025352810496
author Trapeznikov, Kirill
Mancino-Ball, Gabriel
Li, Jonathan
Cummer, Paul
Aslam, Jai
Vahdati, Danial Samadi
Nguyen, Tai
Stamm, Matthew C.
Bautista, Peter
Davinroy, Michael
Cassani, Laura
Crisman, Jill
author_facet Trapeznikov, Kirill
Mancino-Ball, Gabriel
Li, Jonathan
Cummer, Paul
Aslam, Jai
Vahdati, Danial Samadi
Nguyen, Tai
Stamm, Matthew C.
Bautista, Peter
Davinroy, Michael
Cassani, Laura
Crisman, Jill
contents The proliferation of generative video technologies has intensified the need for reliable methods to detect and characterize synthetic media. To address this challenge, we organized the \href{https://safe-video-2025.dsri.org}{SAFE: Synthetic Video Detection Challenge}, co-located with the \textit{Authenticity and Provenance in the Age of Generative AI (APAI) Workshop }at ICCV 2025. The competition invited participants to develop and evaluate algorithms capable of distinguishing real from synthetic videos under fully blind evaluation conditions with over 600 submissions from 12 teams over a 90 day span. Hosted on the Hugging Face platform, the challenge comprised two primary tasks: (1) detection of synthetic video content generated by diverse state-of-the-art models, and (2) detection of synthetic content following common post-processing operations such as resizing, re-compression, motion blur and others. The challenge data consisted of 13 modern high quality synthetic video models with generated content matched to real videos from 21 diverse and challenge sources, all adding up to 20 hours of 6,000 video samples. This paper describes the challenge design, dataset construction, evaluation methodology, and outcomes, offering insights into the generalization and robustness of contemporary synthetic video detection methods. Our findings highlight measurable progress in cross-generator generalization but also persistent vulnerabilities to post-processing artifacts. https://safe-video-2025.dsri.org
format Preprint
id arxiv_https___arxiv_org_abs_2605_06912
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge
Trapeznikov, Kirill
Mancino-Ball, Gabriel
Li, Jonathan
Cummer, Paul
Aslam, Jai
Vahdati, Danial Samadi
Nguyen, Tai
Stamm, Matthew C.
Bautista, Peter
Davinroy, Michael
Cassani, Laura
Crisman, Jill
Computer Vision and Pattern Recognition
The proliferation of generative video technologies has intensified the need for reliable methods to detect and characterize synthetic media. To address this challenge, we organized the \href{https://safe-video-2025.dsri.org}{SAFE: Synthetic Video Detection Challenge}, co-located with the \textit{Authenticity and Provenance in the Age of Generative AI (APAI) Workshop }at ICCV 2025. The competition invited participants to develop and evaluate algorithms capable of distinguishing real from synthetic videos under fully blind evaluation conditions with over 600 submissions from 12 teams over a 90 day span. Hosted on the Hugging Face platform, the challenge comprised two primary tasks: (1) detection of synthetic video content generated by diverse state-of-the-art models, and (2) detection of synthetic content following common post-processing operations such as resizing, re-compression, motion blur and others. The challenge data consisted of 13 modern high quality synthetic video models with generated content matched to real videos from 21 diverse and challenge sources, all adding up to 20 hours of 6,000 video samples. This paper describes the challenge design, dataset construction, evaluation methodology, and outcomes, offering insights into the generalization and robustness of contemporary synthetic video detection methods. Our findings highlight measurable progress in cross-generator generalization but also persistent vulnerabilities to post-processing artifacts. https://safe-video-2025.dsri.org
title Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.06912