用多智能体协作实现更精准的图像匿名化，兼顾隐私保护与图像质量。
Towards Context-Aware Image Anonymization with Multi-Agent Reasoning
- 通过多智能体协同推理，结合空间上下文判断隐私信息。
- 在CUHK03-NP上将重识别率降低73%，关键指标提升显著。
- 支持本地部署、可审计，适合合规要求高的场景使用。
街景图像包含依赖上下文的个人身份信息（PII），现有方法或过度处理，或遗漏隐含标识。我们提出一种基于多智能体推理的上下文感知匿名化框架CAIAMAR，结合扩散模型实现精准匿名化。三类专用智能体在计划-执行-检查-行动循环中轮换协作，利用空间上下文（私有/公共属性）而非固定规则分类PII。采用侦察-放大策略进行粗粒度到细粒度检测，局部裁剪经开放词汇分割，$IoU$阈值为30%的去重机制避免重复处理。模态特异性扩散引导配合外观解耦，显著降低重识别风险。在CUHK03-NP上，人重识别率从62.4%降至16.9%（降幅73%）。在CityScapes上，保持图像质量（KID: 0.001，FID: 9.1），优于现有方法。该流程能识别跨类别间接隐私信息，同时保留下游语义分割能力。系统全本地运行，使用开源模型，生成人类可读审计日志，符合欧盟GDPR透明性要求，并标记需人工复核的失败案例。
原文摘要 · Abstract (English)
Street-level imagery contains personally identifiable information (PII), some of which is context-dependent. Existing anonymization methods either over-process images or miss subtle identifiers, while API-based solutions compromise data sovereignty. We present an agentic framework CAIAMAR (\underline{C}ontext-\underline{A}ware \underline{I}mage \underline{A}nonymization with \underline{M}ulti-\underline{A}gent \underline{R}easoning) for context-aware PII segmentation with diffusion-based anonymization, combining pre-defined processing for high-confidence cases with multi-agent reasoning for indirect identifiers. Three specialized agents coordinate via round-robin speaker selection in a Plan-Do-Check-Act (PDCA) cycle, enabling large vision-language models to classify PII based on spatial context (private vs. public property) rather than rigid category rules. The agents implement spatially-filtered coarse-to-fine detection where a scout-and-zoom strategy identifies candidates, open-vocabulary segmentation processes localized crops, and $IoU$-based deduplication ($30\%$ threshold) prevents redundant processing. Modal-specific diffusion guidance with appearance decorrelation substantially reduces re-identification (Re-ID) risks. On CUHK03-NP, our method reduces person Re-ID risk by $73\%$ ($R1$: $16.9\%$ vs. $62.4\%$ baseline). For image quality preservation on CityScapes, we achieve KID: $0.001$, and FID: $9.1$, significantly outperforming existing anonymization. The agentic workflow detects non-direct PII instances across object categories, and downstream semantic segmentation is preserved. Operating entirely on-premise with open-source models, the framework generates human-interpretable audit trails supporting EU's GDPR transparency requirements while flagging failed cases for human review.
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。