评估视觉语言模型安全性的框架：在公共部门应用中建立对人工智能的信任
A Framework for Evaluating Vision-Language Model Safety: Building Trust in AI for Public Sector Applications
AI总结：
针对视觉语言模型在公共部门应用中的安全性问题，提出量化对抗性风险的框架，通过多种噪声分析识别脆弱区域并引入综合脆弱性评分，以全面评估模型鲁棒性。
摘要：
视觉语言模型（VLMs）越来越多地部署于公共部门任务中，因此亟需对其安全性和对抗性攻击的脆弱性进行稳健评估。本文引入了一种新颖的框架来量化视觉语言模型中的对抗性风险。我们分析了模型在高斯噪声、椒盐噪声和均匀噪声下的性能，识别出误分类阈值，并推导出复合噪声补丁和显著模式，以突出脆弱区域。将这些模式与快速梯度符号法（FGSM）进行比较，以评估其对抗有效性。我们提出了一种新的脆弱性评分，该评分结合了随机噪声和对抗性攻击的影响，为评估模型鲁棒性提供了一个综合指标。
英文摘要：
Vision-Language Models (VLMs) are increasingly deployed in public sector missions, necessitating robust evaluation of their safety and vulnerability to adversarial attacks. This paper introduces a novel framework to quantify adversarial risks in VLMs. We analyze model performance under Gaussian, salt-and-pepper, and uniform noise, identifying misclassification thresholds and deriving composite noise patches and saliency patterns that highlight vulnerable regions. These patterns are compared against the Fast Gradient Sign Method (FGSM) to assess their adversarial effectiveness. We propose a new Vulnerability Score that combines the impact of random noise and adversarial attacks, providing a comprehensive metric for evaluating model robustness.
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。
