Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916867937927168 |
|---|---|
| author | Fang, Chenhao Peng, Yanqing Rao, Rajeev Sarmiento, Matt Summer, Wendy Pudota, Arya Goncalves, Alex Mola, Jordi Robert, Hervé |
| author_facet | Fang, Chenhao Peng, Yanqing Rao, Rajeev Sarmiento, Matt Summer, Wendy Pudota, Arya Goncalves, Alex Mola, Jordi Robert, Hervé |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents Fang, Chenhao Peng, Yanqing Rao, Rajeev Sarmiento, Matt Summer, Wendy Pudota, Arya Goncalves, Alex Mola, Jordi Robert, Hervé Cryptography and Security Artificial Intelligence 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. |
| title | Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2507.21142 |