通过多模态LLM学习AI生成视频中人类感知的虚假性
Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs
AI总结：
该研究推出首个标注人类感知深度伪造痕迹的细粒度时空基准DeeptraceReward，训练多模态奖励模型模拟人类判断，7B模型表现超GPT-5 34.7%，揭示伪造检测难度梯度，为可信视频生成提供测试与训练支撑。
摘要：
人类能否识别AI生成的（虚假）视频并给出有依据的理由？尽管视频生成模型发展迅速，但一个关键维度——人类能否检测生成视频中的深度伪造痕迹，即揭示视频为机器生成的时空锚定视觉伪影——在很大程度上被忽视了。我们推出DeeptraceReward（深度痕迹奖励基准），这是首个细粒度、具备时空感知能力的基准，用于标注人类感知到的虚假痕迹以服务于视频生成奖励。该数据集包含3.3K个高质量生成视频上的4.3K条详细标注。每条标注都提供自然语言解释，精确定位包含感知痕迹的边界框区域，并标记精确的开始和结束时间戳。我们将这些标注整合为9大类导致人类识别视频为AI生成的深度伪造痕迹，并训练多模态语言模型（LM）作为奖励模型，模拟人类的判断和定位能力。在DeeptraceReward基准上，我们的7B参数奖励模型在虚假线索识别、定位和解释三项任务上的平均表现比GPT-5高出34.7%。有趣的是，我们观察到一个一致的难度梯度：真假二分类比细粒度深度伪造痕迹检测容易得多；在后者中，性能从自然语言解释（最易）、空间定位到时间标注（最难）逐步下降。通过聚焦人类感知的深度伪造痕迹，DeeptraceReward为具有社会意识和可信的视频生成提供了严格的测试平台和训练信号。
英文摘要：
Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e., spatiotemporal grounded visual artifacts that reveal a video as machine generated -- has been largely overlooked. We introduce DeeptraceReward, the first fine-grained, spatially- and temporally- aware benchmark that annotates human-perceived fake traces for video generation reward. The dataset comprises 4.3K detailed annotations across 3.3K high-quality generated videos. Each annotation provides a natural-language explanation, pinpoints a bounding-box region containing the perceived trace, and marks precise onset and offset timestamps. We consolidate these annotations into 9 major categories of deepfake traces that lead humans to identify a video as AI-generated, and train multimodal language models (LMs) as reward models to mimic human judgments and localizations. On DeeptraceReward, our 7B reward model outperforms GPT-5 by 34.7% on average across fake clue identification, grounding, and explanation. Interestingly, we observe a consistent difficulty gradient: binary fake v.s. real classification is substantially easier than fine-grained deepfake trace detection; within the latter, performance degrades from natural language explanations (easiest), to spatial grounding, to temporal labeling (hardest). By foregrounding human-perceived deepfake traces, DeeptraceReward provides a rigorous testbed and training signal for socially aware and trustworthy video generation.
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。
