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

2025-05-02

AI Summary

Fine-grained RBAC access control for vector databases faces a fundamental trade-off between storage redundancy and query efficiency (latency/recall). This paper proposes a dynamic overlapping partitioning framework grounded in RBAC policy structure, which—novelty—models the “thin-waist” property of permissions as an optimizable vector replication strategy and establishes a performance-recall analytical model to guide constrained optimization. The method integrates dynamic partitioning, RBAC-aware shared vector indexing, and a hybrid query execution engine to enable permission-aware approximate nearest neighbor search while preserving security guarantees. Experiments demonstrate that, compared to role-specific indexes, our approach reduces storage redundancy by 52%; relative to row-level security schemes, it cuts query latency by 83% with only 1.4× storage overhead. These results significantly enhance the practicality and scalability of secure vector retrieval.

Technology Category

• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Authentication, authorization, and access control

Abstract

As vector databases gain traction in enterprise applications, robust access control has become critical to safeguard sensitive data. Access control in these systems is often implemented through hybrid vector queries, which combine nearest neighbor search on vector data with relational predicates based on user permissions. However, existing approaches face significant trade-offs: creating dedicated indexes for each user minimizes query latency but introduces excessive storage redundancy, while building a single index and applying access control after vector search reduces storage overhead but suffers from poor recall and increased query latency. This paper introduces HoneyBee, a dynamic partitioning framework that bridges the gap between these approaches by leveraging the structure of Role-Based Access Control (RBAC) policies. RBAC, widely adopted in enterprise settings, groups users into roles and assigns permissions to those roles, 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 storage overhead. By introducing analytical models for the performance and recall of the vector search, HoneyBee formulates the partitioning strategy as a constrained optimization problem to dynamically balance storage, query efficiency, and recall. Evaluations on RBAC workloads demonstrate that HoneyBee reduces storage redundancy compared to role partitioning and achieves up to 6x faster query speeds than row-level security (RLS) with only 1.4x storage increase, offering a practical middle ground for secure and efficient vector search.

Problem

• Efficient access control for vector databases via dynamic partitioning
• Balancing storage redundancy and query latency in vector search
• Optimizing RBAC-based partitioning for secure and fast vector queries

Innovation

• Dynamic partitioning framework for RBAC in vector databases
• Overlapping partitions with strategic vector replication
• Constrained optimization balancing storage, query speed, recall