Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases

2026-06-18

AI Summary

This work addresses the critical gap in modern vector databases: the lack of effective support for fine-grained access control (FGAC), which hinders the simultaneous achievement of security compliance, high recall, and low latency. For the first time, FGAC is formally introduced into the vector database domain through a policy-aware vector search framework. The study rigorously defines the FGAC policy model and enforcement problem, and systematically analyzes how policy enforcement mechanisms impact retrieval accuracy and performance. By integrating structured and unstructured attribute modeling, approximate nearest neighbor (ANN) search, and access control policies, the work uncovers inherent tensions among these components, proposes an initial enforcement approach, and identifies key challenges. This foundational effort paves the way for building vector databases that are secure, efficient, and compliant.

Abstract

Vector databases are increasingly used in security sensitive contexts with Retrieval Augmented Generation and organizational AI pipelines; however, their security capabilities remain limited. Specifically, Fine-grained Access Control (FGAC) which is required to ensure that data access adheres to user-specific policies is not fully supported in modern vector databases. Unlike relational databases, vector databases combine structured and unstructured attributes to provide semantic, approximate query results, which complicates FGAC implementation. This creates an inherent tension between enforcing FGAC policies correctly, achieving high ANN search recall and maintaining low query latency. In this paper, we present a vision for Policy-aware Vector Search by formalizing the FGAC policy model in vector databases as well as the enforcement problem. We compare various enforcement strategies, present preliminary findings, and identify key open challenges for future research in policy-aware vector search.

Problem

• Fine-grained Access Control
• Vector Databases
• Policy-aware Vector Search
• Approximate Nearest Neighbor Search
• Access Control Policies

Innovation

• Policy-aware Vector Search
• Fine-grained Access Control
• Vector Databases
• Approximate Nearest Neighbor Search
• Security in AI Pipelines