Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge

• URL: http://arxiv.org/abs/2605.06912v1
• Date: Thu, 07 May 2026 20:22:32 GMT
• Title: Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge
• Abstract summary: SAFE: Synthetic Video Detection Challenge was co-located with the textitAuthenticity and Provenance in the Age of Generative AI (APAI) Workshop at ICCV 2025.<n>The competition invited participants to develop and evaluate algorithms capable of distinguishing real from synthetic videos under fully blind evaluation conditions.<n>Our findings highlight measurable progress in cross-generator generalization but also persistent vulnerabilities to post-processing artifacts.
• Score: 11.327076814364487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore) [130.91833247554004]
  The LoViF 2026 PhyScore challenge is a competition on holistic quality assessment of world-model-generated videos.<n>The benchmark dataset contains 1,554 videos generated by seven representative world generative models.<n>This report summarizes the challenge design and provides method-level insights from submitted solutions.
  arXiv  Detail & Related papers  (2026-05-06T17:52:39Z)
• SynthForensics: A Multi-Generator Benchmark for Detecting Synthetic Video Deepfakes [5.341795386333291]
  We introduce SynthForensics, to the best of our knowledge the first human-centric benchmark for detecting purely synthetic video deepfakes.<n>The benchmark comprises 6,815 unique videos from five architecturally distinct, state-of-the-art open-source T2V models.<n>We observe a mean performance drop of $29.19%$ AUC, with some methods performing worse than random chance, and top models losing over 30 points under heavy compression.
  arXiv  Detail & Related papers  (2026-02-04T16:47:37Z)
• Leveraging Pre-Trained Visual Models for AI-Generated Video Detection [54.88903878778194]
  The field of video generation has advanced beyond DeepFakes, creating an urgent need for methods capable of detecting AI-generated videos with generic content.<n>We propose a novel approach that leverages pre-trained visual models to distinguish between real and generated videos.<n>Our method achieves high detection accuracy, above 90% on average, underscoring its effectiveness.
  arXiv  Detail & Related papers  (2025-07-17T15:36:39Z)
• DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning [58.70446237944036]
  DAVID-X is the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales.<n>We present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning.<n>Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.
  arXiv  Detail & Related papers  (2025-06-13T13:39:53Z)
• AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection [20.800161778433914]
  Human-centric video generation methods can synthesize entire human bodies with controllable movements.<n>Existing detection methods largely overlook the growing risks posed by such full-body synthetic content.<n>We propose AvatarShield, a novel multimodal human-centric synthetic video detection framework.
  arXiv  Detail & Related papers  (2025-05-21T06:43:34Z)
• BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation [77.55074597806035]
  GenBuster-200K is a large-scale, high-quality AI-generated video dataset featuring 200K high-resolution video clips.<n>BusterX is a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-19T02:06:43Z)
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations [120.52120919834988]
  xGen-SynVideo-1 is a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens. DiT model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios.
  arXiv  Detail & Related papers  (2024-08-22T17:55:22Z)
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study [95.36629866768999]
  This paper introduces a novel dataset for video enhancement and studies the state-of-the-art methods of the NTIRE 2021 challenge. The challenge is the first NTIRE challenge in this direction, with three competitions, hundreds of participants and tens of proposed solutions. We find that the NTIRE 2021 challenge advances the state-of-the-art of quality enhancement on compressed video.
  arXiv  Detail & Related papers  (2021-04-21T22:18:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.