Skip to main content

HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning

Journal articles
Zhong, H; Lentz, M; Narodytska, N; Szekeres, A; Rong, K
Published in: Proceedings of the ACM on Management of Data
April 2, 2026

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Proceedings of the ACM on Management of Data

DOI

EISSN

2836-6573

Publication Date

April 2, 2026

Volume

4

Issue

1

Start / End Page

1 / 26

Publisher

Association for Computing Machinery (ACM)
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhong, H., Lentz, M., Narodytska, N., Szekeres, A., & Rong, K. (2026). HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning. Proceedings of the ACM on Management of Data, 4(1), 1–26. https://doi.org/10.1145/3786625
Zhong, Hongbin, Matthew Lentz, Nina Narodytska, Adriana Szekeres, and Kexin Rong. “HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning.” Proceedings of the ACM on Management of Data 4, no. 1 (April 2, 2026): 1–26. https://doi.org/10.1145/3786625.
Zhong H, Lentz M, Narodytska N, Szekeres A, Rong K. HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning. Proceedings of the ACM on Management of Data. 2026 Apr 2;4(1):1–26.
Zhong, Hongbin, et al. “HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning.” Proceedings of the ACM on Management of Data, vol. 4, no. 1, Association for Computing Machinery (ACM), Apr. 2026, pp. 1–26. Crossref, doi:10.1145/3786625.
Zhong H, Lentz M, Narodytska N, Szekeres A, Rong K. HONEYBEE: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning. Proceedings of the ACM on Management of Data. Association for Computing Machinery (ACM); 2026 Apr 2;4(1):1–26.

Published In

Proceedings of the ACM on Management of Data

DOI

EISSN

2836-6573

Publication Date

April 2, 2026

Volume

4

Issue

1

Start / End Page

1 / 26

Publisher

Association for Computing Machinery (ACM)