PulseAugur
LIVE 07:19:37
research · [1 source] ·
0
research

Onyx offers cost-efficient, disk-oblivious ANN search for sensitive data

Researchers have developed Onyx, a new system for approximate nearest neighbor (ANN) search designed to protect sensitive data when processed on external storage. Onyx addresses the high costs and latency associated with existing oblivious ANN search methods by co-designing its ANN and ORAM components. The system achieves significant improvements, offering 1.7-9.9x lower cost and 2.3-12.3x lower latency compared to prior state-of-the-art solutions. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances privacy for sensitive data in AI systems, potentially enabling more secure third-party processing.

RANK_REASON Academic paper introducing a novel system for secure data search.

Read on Hugging Face Daily Papers →

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 ·

    Onyx: Cost-Efficient Disk-Oblivious ANN Search

    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 acce…