MESS：基于多图HNSW的快速私有语义搜索
MESS: Fast and Private Semantic Search on Multi-Graph HNSW
浏览论文内容
中文总结 AI 辅助
本文提出MESS系统，通过映射向量为二进制编码、应用LSH和随机响应、构建多图HNSW索引，实现兼具隐私性、准确性、高效性的语义搜索，延迟较最优基线低达15.08倍。
中文摘要 AI 辅助
语义搜索系统将数据映射到高维向量空间，支持通过近似最近邻搜索检索相似数据。当系统由可信云提供商托管时，数据或查询不存在隐私保护。本文旨在设计兼具隐私性、准确性和高效性的系统。现有工作采用同态加密（HE）、 obliviousness RAM（ORAM）或差分隐私（DP）方法，但无法同时实现这三种属性。本文提出MESS系统，其将原始向量映射为二进制编码，应用局部敏感哈希（LSH）和随机响应，在扰动后的编码上构建多图分层可导航小世界（HNSW）索引。MESS确保数据、查询和访问模式隐私，还通过两阶段查询扰动机制确保搜索模式隐私；多图索引缓解扰动对结果质量的影响，实现准确性；且因直接在扰动编码上搜索，无需HE或ORAM开销，具备高效性。本文对系统隐私性进行形式分析，并对性能开展广泛评估，结果显示MESS的延迟比现有最优基线低达15.08倍。
英文摘要
Semantic search systems map data to a high-dimensional vector space and support retrieval of similar data via approximate nearest neighbor search. When the system is hosted by an untrusted cloud provider, there is no privacy for the data or the query. Our goal is to design a system with three properties: privacy, accuracy, and efficiency. Existing works adopt either homomorphic encryption (HE), oblivious RAM (ORAM), or a differential privacy (DP) approach. They fall short of achieving all three properties. In this paper, we present MESS, a system that realizes our goal. It maps the original vectors into binary codes, applies locality-sensitive hashing (LSH) and randomized response, and constructs a multi-graph Hierarchical Navigable Small World (HNSW) index over the perturbed codes. MESS ensures data, query, and access pattern privacy. It also ensures search pattern privacy via a two-phase query perturbation mechanism. The multi-graph index mitigates the impact of perturbation on result quality, thereby achieving accuracy. MESS is efficient because search is performed directly over perturbed codes, without the overhead of homomorphic encryption or ORAM. We give formal analysis of the system's privacy and extensive evaluation of its performance. The results show that MESS achieves up to 15.08\times lower latency than state-of-the-art baselines.
