HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning
Open Access
- 2 April 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (1) , 1-26
Abstract
Enterprise deployments of vector databases require access control policies to protect sensitive data. These systems often implement access control through hybrid vector queries that combine nearest-neighbor search with relational predicates based on user permissions. However, existing approaches face a fundamental trade-off: dedicated per-user indexes minimize query latency but incur high memory redundancy, while shared indexes with post-search filtering reduce memory overhead at the cost of increased latency. This paper introduces HONEYBEE, a dynamic partitioning framework that leverages the structure of Role-Based Access Control (RBAC) policies to create a smooth trade-off between these extremes. RBAC policies organize users into roles and assign permissions at the role level, creating a natural ''thin waist'' in the permission structure that is ideal for partitioning decisions. Specifically, HONEYBEE produces overlapping partitions where vectors can be strategically replicated across different partitions to reduce query latency while controlling memory overhead. To guide these decisions, HONEYBEE develops analytical models of vector search performance and recall, and formulates partitioning as a constrained optimization problem that balances memory usage, query efficiency, and recall. Evaluations on RBAC workloads demonstrate that HONEYBEE achieves up to 13.5X lower query latency than row-level security with only a 1.24X increase in memory usage, while achieving comparable query performance to dedicated, per-role indexes with 90.4% reduction in additional memory consumption, offering a practical middle ground for secure and efficient vector search.Keywords
All Related Versions
Funding Information
- National Science Foundation (IIS-2335881)
This publication has 23 references indexed in Scilit:
- Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers2024
- Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors2018
- New method for the on-line signature verification based on horizontal partitioningPattern Recognition, 2014
- Product Quantization for Nearest Neighbor SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Horizontal Partitioning by Predicate Abstraction and Its Application to Data Warehouse Design2010
- Supporting Database Applications as a ServiceInternational Conference on Data Engineering, 2009
- High dimensional nearest neighbor searchingInformation Systems, 2006
- Integrating vertical and horizontal partitioning into automated physical database design2004
- Algorithms and Support for Horizontal Class Partitioning in Object-Oriented DatabasesDistributed and Parallel Databases, 2000
- Role-based access control modelsComputer, 1996