当眼见不再为实——面向搜索辅助的视频虚假信息检测基准
When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection
AI总结：
提出EVID-Bench基准，通过跨视频对比和开放网络搜索检测视频虚假信息，涵盖9种操纵类型，评估前沿多模态模型发现准确率低且面临多种挑战。
摘要：
视频虚假信息越来越多地在语义和证据层面运作：真实镜头可能被选择性编辑、时间重排、跨源拼接或通过AI生成内容增强以构建虚假叙事。这种依赖证据的操纵无法仅从输入视频中可靠验证，因为缺失、重排、替换或重新语境化的证据位于视频本身之外。我们引入了 extbf{EVID-Bench}，一个面向搜索辅助的视频虚假信息检测基准，系统必须搜索开放网络以查找相关视频，并通过跨视频比较识别哪些信息是虚假的。EVID-Bench包含222个视频，涵盖3类9种操纵类型：AI生成、单源编辑和多源编辑。所有样本均经过验证，前沿模型仅通过视觉检查无法检测。我们使用检索增强验证基线评估了九种前沿多模态模型。最佳系统仅达到61.43%的点级准确率和43.24%的视频级准确率，而AI生成的操纵仍然特别具有挑战性。错误分析揭示了反复出现的挑战：模型固着于无关锚点，错误地将合成内容归因于编辑拼接，并在完全解释操纵之前过早终止搜索。
英文摘要：
Video misinformation increasingly operates at the semantic and evidential level: authentic footage may be selectively edited, temporally reordered, spliced across sources, or augmented with AI-generated content to construct false narratives. Such evidence-dependent manipulations cannot be reliably verified from the input video alone, because the missing, reordered, replaced, or recontextualized evidence lies outside the video itself. We introduce \textbf{EVID-Bench}, a benchmark for search-grounded video misinformation detection, where a system must search the open web for related videos and identify what information is false through cross-video comparison. EVID-Bench comprises 222 videos spanning 9 manipulation types across 3 categories: AI generation, single-source editing, and multi-source editing. All samples are verified to be undetectable by frontier models through visual inspection alone. We evaluate nine frontier multimodal models using a retrieval-augmented verification baseline. The best system achieves only 61.43\% point-level accuracy and 43.24\% video-level accuracy, while AI-generated manipulations remain especially challenging. Error analysis reveals recurring challenges: models fixate on irrelevant anchors, misattribute synthetic content to editorial splicing, and terminate search prematurely before fully explaining the manipulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
