SynCred-Bench: 评估AI生成视觉虚假信息中的合成可信度
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
AI总结：
提出SynCred-Bench基准，包含600个AI生成的虚假信息图像，涵盖六种可信形式和七种传播风格，并引入FP450真实图像负集，评估显示现有系统在5%假阳性率下真阳性率极低，表明合成可信度是一个严重且未被充分探索的视觉虚假信息挑战。
摘要：
最近的生成模型能够生成带有逼真嵌入文本和布局的视觉制品，创造了一种新的虚假信息威胁：合成可信度。我们引入了SYNCRED-Bench，一个包含600个AI生成的虚假信息图像的基准，这些图像在六种可信形式类别和七种细粒度传播风格上平衡分布，同时还有FP450，一个用于测量假阳性的真实图像负集。广泛评估表明，现有系统仍然不可靠：在5%假阳性率约束下，15个多模态大语言模型仅达到10.5%的真阳性率，开源AIGC检测器达到不到5%，商业API达到57.6%。人类标注者也难以识别合成可信度，仅达到63%的真阳性率。这些发现将合成可信度确立为一个严重且未被充分探索的视觉虚假信息挑战，并提供了一个基准，用于开发超越表面可信度线索进行推理的检测器。
英文摘要：
Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility. We introduce SYNCRED-Bench, a benchmark of 600 AI-generated misinformation images balanced across six credible-form categories and seven fine-grained circulation styles, together with FP450, a real-image negative set for measuring false positives. Extensive evaluation shows that existing systems remain unreliable: under a 5% false-positive-rate constraint, 15 MLLMs achieve only 10.5% true positive rate (TPR), open-source AIGC detectors achieve less than 5%, and commercial APIs reach 57.6%. Human annotators also struggled to identify synthetic credibility, reaching only 63% TPR. These findings establish synthetic credibility as a severe and underexplored visual misinformation challenge, and provide a benchmark for developing detectors that reason beyond superficial credibility cues.
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。
