Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
This work addresses the need for FGAC in vector databases for security-sensitive applications, but it is a vision paper with preliminary results, making it incremental.
The paper identifies the lack of fine-grained access control (FGAC) in vector databases, which is critical for security-sensitive applications like RAG. It formalizes the FGAC policy model and enforcement problem, compares strategies, and presents preliminary findings, highlighting open challenges.
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.