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.