[Resource Topic] 2024/1255: Compass: Encrypted Semantic Search with High Accuracy

Welcome to the resource topic for 2024/1255

Title:
Compass: Encrypted Semantic Search with High Accuracy

Authors: Jinhao Zhu, Liana Patel, Matei Zaharia, Raluca Ada Popa

Abstract:

We introduce Compass, a semantic search system over encrypted data that offers high accuracy, comparable to state-of-the-art plaintext search algorithms while protecting data, queries and search results from a fully compromised server. Compass also enables privacy-preserving RAG where both the RAG database and the query are protected. Compass’s search index contributes a novel way to traverse the search graph in Hierarchical Navigable Small Worlds (HNSW), a top performing vector nearest neighbor search, using Oblivious RAM, a cryptographic primitive with strong security guarantees. Our techniques, Directional Neighbor Filtering, Speculative Greedy Search and HNSW-tailored Path ORAM ensure that Compass achieves user-perceived latencies of few seconds and is orders of magnitude faster than a baseline for encrypted embeddings search.

ePrint: https://eprint.iacr.org/2024/1255

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .