面向儿童的AIGC视频风险审查：一个基准和知识支持的迭代推理框架

中文摘要 AI 辅助

人工智能生成内容（AIGC）的快速增长正在重塑视频制作和传播，使儿童接触到越来越多的AIGC视频。与传统制作的视频不同，AIGC视频在视觉细节、叙事连贯性和内容表达方面往往表现出更大的不确定性，这可能给儿童带来发育上不适当的风险。现有视频安全研究大多从成人角度进行一般违规检测，不足以识别儿童观看AIGC视频时可能遇到的细粒度、隐含和上下文相关的风险。为填补这一空白，我们研究面向儿童的AIGC视频审查，有三项贡献。首先，构建CAVSR基准，开发分层风险分类法。其次，提出QVRS-E框架，结合多智能体协作与知识经验支持有针对性的证据获取和基于事实的审查决策。最后，大量实验表明我们的方法显著增强了与视觉语言模型集成的儿童相关风险审查，并产生更可靠的审查报告。

英文摘要

The rapid growth of Artificial Intelligence-generated content (AIGC) is reshaping video production and circulation, exposing children to an increasing volume of AIGC videos. Unlike traditionally produced videos, AIGC videos often exhibit greater uncertainty in visual details, narrative coherence, and content expression, which may introduce developmentally inappropriate risks for children. However, existing video safety research is largely designed for general violation detection from an adult perspective and remains insufficient for identifying the fine-grained, implicit, and context-dependent risks that children may encounter when viewing AIGC videos. To address this gap, we study child-oriented AIGC video reviewing, making three contributions. First, we construct CAVSR, a benchmark of 605 real-world videos collected from multiple platforms, and develop a hierarchical risk taxonomy comprising 6 top-level categories and 26 fine-grained labels to support systematic evaluation of children's viewing risks. Second, we propose QVRS-E, a knowledge- and experience-augmented video reviewing framework that combines multi-agent collaboration with expert and experiential knowledge to support targeted evidence acquisition and fact-grounded reviewing decisions. Third, extensive experiments demonstrate that our method significantly enhances the reviewing of child-related risks integrated with vision-language models, and yields more robust review reports.

发表机构

• Shandong University（山东大学）
• Fudan University（复旦大学）
• Beijing Jiaotong University（北京交通大学）

机构由 AI 辅助整理，请以论文原文为准。