Onyx: Cost-Efficient Disk-Oblivious ANN Search

2026-04-22

AI Summary

This work addresses the privacy risks and inefficiencies of performing approximate nearest neighbor (ANN) search on third-party infrastructure, where disk access patterns to external SSDs can leak user queries. Existing ORAM-based solutions suffer from high monetary cost, latency, and poor resource utilization. To overcome these limitations, the authors propose Onyx, a co-designed system that inverts the conventional paradigm by jointly optimizing the ANN and ORAM layers. Specifically, Onyx introduces a bandwidth-aware compact intermediate representation (Onyx-ANNS) at the ANN layer to minimize data transfer volume and a locality-aware shallow tree structure (Onyx-ORAM) at the ORAM layer to reduce the number of accesses. This synergistic design achieves substantial improvements in resource efficiency, yielding 1.7–9.9× lower cost and 2.3–12.3× reduced latency compared to the state-of-the-art.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

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

Abstract

Approximate nearest neighbor (ANN) search in AI systems increasingly handles sensitive data on third-party infrastructure. Trusted execution environments (TEEs) offer protection, but cost-efficient deployments must rely on external SSDs, which leaks user queries through disk access patterns to the host. Oblivious RAM (ORAM) can hide these access patterns but at a high cost; when paired with existing disk-based ANN search techniques, it makes poor use of SSD resources, yielding high latency and poor cost-efficiency. The core challenge for efficient oblivious ANN search over SSDs is balancing both bandwidth and access count. The state-of-the-art ORAM-ANN design minimizes access count at the ANN level and bandwidth at the ORAM level, each trading-off the other, leaving the combined system with both resources overutilized. We propose inverting this design, minimizing bandwidth consumption in the ANN layer and access count in the ORAM layer, since each component is better suited for its new role: ANN's inherent approximation allows for more bandwidth efficiency, while ORAM has no fundamental lower bounds on access count (as opposed to bandwidth). To this end, we propose a cost-efficient approach, Onyx, with two new co-designed components: Onyx-ANNS introduces a compact intermediate representation that proactively prunes the majority of bandwidth-intensive accesses without hurting recall, and Onyx-ORAM proposes a locality-aware shallow tree design that reduces access count while remaining compatible with bandwidth-efficient ORAM techniques. Compared to the state-of-the-art oblivious ANN search system, Onyx achieves $1.7-9.9\times$ lower cost and $2.3-12.3\times$ lower latency.

Problem

• Approximate Nearest Neighbor
• Trusted Execution Environments
• Oblivious RAM
• SSD
• Privacy-Preserving Search

Innovation

• oblivious ANN search
• ORAM
• cost-efficiency
• bandwidth optimization
• access pattern hiding