重新思考视觉隐私：一种用于严重性评估的组合隐私风险框架与VLM
Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
AI总结：
提出组合隐私风险分类法（CPRT），将视觉属性按独立可识别性和组合危害潜力分级，并构建6.7K图像数据集，评估VLM在组合隐私风险评估中的表现。
摘要：
现有的视觉隐私基准大多将隐私视为二元属性，根据可见的敏感内容将图像标记为私密或非私密。我们认为隐私本质上是组合的。单独无害的属性组合起来可能产生严重的隐私侵犯。我们引入了组合隐私风险分类法（CPRT），这是一个基于法规的框架，根据独立可识别性和组合危害潜力组织视觉属性。CPRT定义了四个分级严重性级别，并配有一个可解释的评分函数，用于分配连续的隐私严重性分数。我们进一步构建了一个与分类法对齐的6.7K图像数据集，并推导出组合风险分数。通过评估前沿和开放权重的VLM，我们发现前沿模型在提供结构化指导时与组合严重性对齐良好，但系统性地低估了组合驱动的风险。较小的模型难以内化分级隐私推理。为弥补这一差距，我们引入了一个可部署的8B SFT模型，该模型在组合隐私评估上接近前沿水平。
英文摘要：
Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations. We introduce the Compositional Privacy Risk Taxonomy (CPRT), a regulation-aware framework that organizes visual attributes according to standalone identifiability and compositional harm potential. CPRT defines four graded severity levels and is paired with an interpretable scoring function that assigns continuous privacy severity scores. We further construct a taxonomy-aligned dataset of 6.7K images and derive compositional risk scores. By evaluating frontier and open-weight VLMs we find that frontier models align well with compositional severity when provided structured guidance, but systematically underestimate composition-driven risks. Smaller models struggle to internalize graded privacy reasoning. To bridge this gap, we introduce a deployable 8B SFT model that closely matches frontier-level performance on compositional privacy assessment
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。
