构建企业隐私合规知识图谱，让AI自动发现跨系统数据风险
Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents
- 用文本嵌入技术连接代码、数据等多类企业资产
- 召回率从18%升至53%，查询匹配率提升至69.7%
- 适合安全合规团队和AI助手开发人员使用
企业环境包含大量异构、快速增长的内部资源，涵盖代码、数据及各类工具。评估隐私风险与确保合规性的关键信息常分散在这些不同资源中，每类资源均有复杂的发现与提取方式。因此，大规模隐私合规需建立能理解跨资源关联的统一系统。我们提出隐私资产连接器（PACT），一个基于嵌入的图谱，可链接数百万种由不同团队和项目生成的异构资产。PACT采用先进的DRAGON嵌入模型，通过对比学习与轻量微调，依据元数据、归属信息及合规上下文等文本内容关联资产。实验表明，经过微调的PACT模型使召回率@1从18%提升至53%，与基线AI代理配合时查询匹配率从9.6%增至69.7%，在标准推荐系统中的命中率@1从25.7%提高到44.9%。
原文摘要 · Abstract (English)
Enterprise environments contain a heterogeneous, rapidly growing collection of internal artifacts related to code, data, and many different tools. Critical information for assessing privacy risk and ensuring regulatory compliance is often embedded across these varied resources, each with their own arcane discovery and extraction techniques. Therefore, large-scale privacy compliance in adherence to governmental regulations requires systems to discern the interconnected nature of diverse artifacts in a common, shared universe. We present Privacy Artifact ConnecT or (PACT), an embeddings-driven graph that links millions of artifacts spanning multiple artifact types generated by a variety of teams and projects. Powered by the state-of-the-art DRAGON embedding model, PACT uses a contrastive learning objective with light fine-tuning to link artifacts via their textual components such as raw metadata, ownership specifics, and compliance context. Experimental results show that PACT's fine-tuned model improves recall@1 from 18% to 53%, the query match rate from 9.6% to 69.7% when paired with a baseline AI agent, and the hitrate@1 from 25.7% to 44.9% for candidate selection in a standard recommender system.
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。