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

Summary: Honeybee tackles RBAC for vector DBs via dynamic overlapping partitioning, exploiting the role/permission “thin waist” to choose vector replication adaptively. Analytic latency/recall models drive constrained optimization, yielding a middle ground between per-user indexes and shared post-filtering. (summarized by gpt-5-mini on Apr 11 2026)

Paper ID: 7642
Venue: SIGMOD
Year: 2026
Pagerank: 5.093636e-05
Overall Rank: 10,430 | 28.45%
DOI: 10.1145/3786625

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Hongbin Zhong (Georgia Institute of Technology)
2. Matthew Lentz (Duke University)
3. Nina Narodytska (VMware Research by Broadcom)
4. Adriana Szekeres (Microsoft)
5. Kexin Rong (Georgia Institute of Technology)

BibTeX Citation

@inproceedings{zhong_sigmod26,
        title = {{Honeybee: Efficient Role-based Access Control for Vector Databases via Dynamic Partitioning}},
        author = {Zhong, Hongbin and Lentz, Matthew and Narodytska, Nina and Szekeres, Adriana and Rong, Kexin},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3786625},
        url = {https://dl.acm.org/doi/10.1145/3786625},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 12 of 12 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
21	Similarity Search in High Dimensions via Hashing	1999	VLDB	0.00056760516
93	Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph	2019	VLDB	0.00034701237
199	Integrating Vertical and Horizontal Partitioning into Automated Physical Database Design	2004	SIGMOD	0.00025612088
926	Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination	2020	SIGMOD	0.00013181732
1,135	Qd-tree: Learning Data Layouts for Big Data Analytics	2020	SIGMOD	0.00012032847
1,515	ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data	2024	SIGMOD	0.00010521317
1,631	High-Throughput Vector Similarity Search in Knowledge Graphs	2023	SIGMOD	0.00010174628
2,855	Horizontal Data Partitioning In Database Design	1982	SIGMOD	8.0323779e-05
3,035	Instance-Optimized Data Layouts for Cloud Analytics Workloads	2021	SIGMOD	7.8297746e-05
3,286	iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search	2024	SIGMOD	7.5596483e-05
6,042	Pando: Enhanced Data Skipping with Logical Data Partitioning	2023	VLDB	5.9970052e-05
9,377	LeaFi: Data Series Indexes on Steroids with Learned Filters	2025	SIGMOD	5.2755515e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	8,214	Tuning Hierarchical Learned Indexes on Disk and Beyond	2022	SIGMOD
2	10,350	Building Stateless Serverless Vector DBs via Block-based Data Partitioning	2026	SIGMOD
3	10,395	RABIT: Efficient Range Queries with Bitmap Indexing	2026	SIGMOD
4	7,585	Query Centric Partitioning and Allocation for Partially Replicated Database Systems	2017	SIGMOD
5	8,872	Cost-Effective, Low Latency Vector Search with Azure Cosmos DB	2025	VLDB
6	10,571	An Experimental Evaluation of Hybrid Querying on Vectors	2026	VLDB
7	10,449	Efficient Vector Index Merging in Vector Databases	2026	SIGMOD
8	10,439	Curator: Efficient Vector Search with Low-Selectivity Filters	2026	SIGMOD
9	9,778	Turbocharging Vector Databases using Modern SSDs	2025	VLDB
10	10,765	HoneyComb: A Parallel Worst-Case Optimal Join on Multicores	2025	SIGMOD