人工智能生成的图像在高风险场景中挑战视觉信任
AI-generated Images Challenge Visual Trust in High-risk Scenarios
AI总结：
研究聚焦人工智能生成图像在高风险场景下对视觉信任的挑战，提出SafeIMG基准，涵盖12个安全场景。评估专门探测器和视觉语言模型，发现它们检测可靠性不足，模型解释覆盖低，表明当前探测器在多方面欠缺，难以可靠评估此类图像。
AI中文摘要：
图像生成技术的快速发展正在侵蚀视觉内容在真实性会影响公共安全和个人声誉的场景中的证据价值。现有检测基准很少在公共和个人安全背景下检验合成图像，而误导性视觉内容可能带来重大风险。本文介绍了SafeIMG，这是一个面向安全的基准，涵盖12个使用GPT Image 2生成的公共和个人安全场景。它不仅评估探测器是否能识别合成图像，还评估其决策是否反映人类识别出的异常。通过人工标注来定位可疑区域并解释局部伪像以及更高层次的常识或物理不一致性。对专门的合成图像探测器和视觉语言模型进行评估，发现它们都不能提供可靠检测。最强的视觉语言模型只能识别49.5%的生成图像，最好的专门探测器识别率为33.1%，而人类评估者的准确率为81.7%。模型解释仅涵盖29.8%的人工标注异常，且在传播导致图像退化后检测性能进一步恶化。这些发现表明当前探测器在跨公共和个人安全设置可靠评估人工智能生成图像方面缺乏准确性、解释一致性和鲁棒性。
英文摘要：
Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation. Yet existing detection benchmarks rarely examine synthetic images in public- and individual-safety contexts, where misleading visual content may carry substantial risks. Here we introduce SafeIMG, a safety-oriented benchmark spanning 12 public- and individual-safety scenarios generated using GPT Image 2. Unlike benchmarks centred on generic imagery and image-level labels, SafeIMG evaluates not only whether detectors recognise synthetic images, but also whether their decisions reflect human-identified anomalies. To this end, SafeIMG provides human annotations that localise suspicious regions and explain local artefacts and higher-level commonsense or physical inconsistencies. We evaluate specialized synthetic-image detectors and vision-language models (VLMs), and find that neither provides reliable detection. The strongest VLM identifies only 49.5% of generated images, whereas the best specialised detector identifies 33.1%, compared with 81.7% accuracy for human evaluators. Model explanations cover only 29.8\% of human-annotated anomalies and predominantly capture local defects in text, faces and hands. Their coverage falls to 15.0% for commonsense conflicts and 12.0% for physical inconsistencies, while detection performance deteriorates further after dissemination-induced image degradation. These findings show that current detectors lack the accuracy, explanatory alignment and robustness needed to evaluate AI-generated images reliably across public- and individual-safety settings.
