构建首个用户级多模态隐私泄露评估基准，提升隐私风险识别能力
What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media
- 基于真实数据抽象泄露模式，构建合成基准SopriBench
- 提出隐私暴露评分PES，按上下文敏感度加权粒度
- 开发无需训练的推理框架Argus，精准捕捉跨帖子累积泄露
公开社交帖子可通过文本、图像或元数据中的微弱线索泄露隐私信息。这种泄露常具累积性和跨帖子特征：单个线索看似无害，但组合后可能暴露用户的住址、工作地点或日常规律。现有研究缺乏统一的用户级多模态隐私泄露评估基准，且评价指标仅关注二值准确率，无法衡量暴露严重程度。为此，我们提出SopriBench，一个基于红笔记（Rednote）和Instagram账户私有语料库抽象出的泄露模式构建的合成基准，涵盖50个用户账号、1,569张图像，包含属性、情境敏感度、粒度、泄露类型、推理难度及支持证据等维度。我们进一步引入隐私暴露评分（PES），根据情境敏感度对信息粒度进行加权。受溯因推理启发，我们设计Argus——一种无需训练的代理式框架，可聚合证据形成假设、验证支持证据，并将跨帖子线索整合为隐私画像，实现0.55 PES，较最强基线提升25%，尤其在跨帖子泄露场景中增益显著。
原文摘要 · Abstract (English)
Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that appear harmless in isolation may jointly expose a user's home, workplace, or routine. However, current research lacks a unified benchmark for user-level multimodal privacy leakage and an evaluation metric that captures exposure severity beyond binary accuracy. To address these gaps, we propose SopriBench, a synthetic benchmark guided by leakage patterns abstracted from a private reference corpus of Rednote and Instagram accounts, covering 50 user profiles and 1,569 images with attributes, contextual sensitivity, granularity, leakage type, inference difficulty, and supporting evidence. We further introduce the Privacy Exposure Score (PES), which weights value granularity by contextual sensitivity. Inspired by abductive reasoning, we introduce Argus, a training-free agentic framework for cumulative leakage inference. Argus forms hypotheses from accumulated evidence, verifies supporting evidence, and aggregates cross-post cues into privacy profiles, achieving 0.55 PES, a 25% improvement over the strongest baseline, with the largest gain on cross-post leakage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。