Vectors are used to represent unstructured data with their embeddings and associated attributes. Similarity search over large-scale vector datasets has gained significant interest from both industry and academia. It aims to identify the k nearest neighbors to a query object from vectors that satisfy a given attribute filter constraint. Despite its popularity, most solutions focus on single-sourced data and overlook the need for vector retrieval across federated datasets. To fill this gap, we introduce a new problem, federated vector similarity search with filters, which enables privacy-preserving vector retrieval over multi-sourced data held by mutually untrusted providers. While some solutions can be adapted, they struggle with low recall, excessive search latency, or high communication cost. To address these challenges, we propose FedVS, a privacy-preserving framework enhanced with indexing and pruning based on Trusted Execution Environment (TEE). We also provide a comprehensive theoretical analysis, including complexity, security, and approximation guarantees for recall. Moreover, we deploy our solution over real-world vector databases and conduct extensive experiments. The results demonstrate that our solution outperforms state-of-the-art methods in both effectiveness and efficiency.

Efficient vector search is a foundational capability of vector databases. However, most prior research overlooks its critical role in federated databases for applications like financial risk control and smart healthcare. In these privacy-sensitive scenarios, a vector search engine must not only deliver high performance but also guarantee privacy across federated databases. Current solutions, however, struggle with scalability for high-dimensional vectors, and offer limited query support. To bridge this gap, this paper introduces FedVSE, a privacy-preserving vector search engine for federated databases. FedVSE supports both KNN and hybrid queries, matching the versatility of modern vector databases. It leverages Intel SGX for hardware-enabled security and offers highly optimized query processing via indexing and pruning. Conference audiences can interact with FedVSE in real time and observe how it enables real-world services like cross-platform trajectory similarity search.

Vector databases have emerged as crucial tools for managing and retrieving representation embeddings of unstructured data. Given the explosive growth of data, vector data is often distributed and stored across multiple organizations. However, privacy concerns and regulations like GDPR present new challenges in collaborative and secure queries, also known as federated queries, over those vector data distributed across various data owners. Although existing research has attempted to enable such query services for low-dimensional data, such as relational and spatial data, these solutions can be inefficient in answering vector similarity queries involving high-dimensional data. Therefore, we are motivated to develop a new prototype system called FedSQ that (1) ensures privacy protection across data owners and (2) balances query efficiency and result accuracy when processing federated vector similarity queries. To achieve these goals, FedSQ utilizes advanced secure multi-party computation techniques to prevent information leakage during query processing and incorporates indexing and sampling based optimizations to strike a proper performance balance.