Modern AI and vector search are rapidly converging, forming a promising research frontier in intelligent information systems. On one hand, advances in AI have substantially improved the semantic accuracy and efficiency of vector search, including learned indexing structures, adaptive pruning strategies, and automated parameter tuning. On the other hand, powerful vector search techniques have enabled new AI paradigms, notably Retrieval-Augmented Generation (RAG), which effectively mitigates challenges in Large Language Models (LLMs) like knowledge staleness and hallucinations. This mutual reinforcement establishes a virtuous cycle where AI injects intelligence and adaptive optimization into vector search, while vector search, in turn, expands AI's capabilities in knowledge integration and context-aware generation. This tutorial provides a comprehensive overview of recent research and advancements at this intersection. We begin by discussing the foundational background and motivations for integrating vector search and AI. Subsequently, we explore how AI empowers vector search (AI4VS) across each step of the vector search pipeline. We then investigate how vector search empowers AI (VS4AI), with a particular focus on RAG frameworks that integrate dynamic, external knowledge sources into the generative process of LLMs. Furthermore, we analyze end-to-end co-optimization strategies that fully unlock the potential of the ``virtuous cycle" between vector search and AI. Finally, we highlight key challenges and future research opportunities in this emerging area. This paper was published in ICDE 2026.

Locality-sensitive hashing (LSH) is a well-known solution for approximate nearest neighbor (ANN) search with theoretical guarantees. Traditional LSH-based methods mainly focus on improving the efficiency and accuracy of query phase by designing different query strategies, but pay little attention to improving the efficiency of the indexing phase. They typically fine tune existing data-oriented partitioning trees to index data points and support their query strategies. However, their strategy to directly partition the multidimensional space is time-consuming, and performance degrades as the space dimensionality increases. In this paper, we design an encoding-based tree called Dynamic Encoding Tree (DE-Tree) to improve the indexing efficiency and support efficient range queries. Based on DE-Tree, we propose a novel LSH scheme called DET-LSH. DET-LSH adopts a novel query strategy, which performs range queries in multiple independent index DE-Trees to reduce the probability of missing exact NN points. Extensive experiments demonstrate that while achieving best query accuracy, DET-LSH achieves up to 6x speedup in indexing time and 2x speedup in query time over the state-of-the-art LSH-based methods. In addition, to further improve the performance of DET-LSH, we propose PDET-LSH, an in-memory method adopting the parallelization opportunities provided by multicore CPUs. PDET-LSH exhibits considerable advantages in indexing and query efficiency, especially on large scale datasets. Extensive experiments show that, while achieving the same query accuracy as DET-LSH, PDET-LSH offers up to 40x speedup in indexing time and 62x speedup in query answering time over the state-of-the-art LSH-based methods. Our theoretical analysis demonstrates that DET-LSH and PDET-LSH offer probabilistic guarantees on query answering accuracy.

Access control is a security mechanism designed to ensure that only authorized users can access specific resources. Cross-domain access control involves access to resources across different organizations, institutions, or applications. Traditional access control, however, which handles authentication and authorization separately in centralized environments, faces challenges in identity dispersion, privacy leakage, and diversified permission requirements, failing to adapt to cross-domain scenarios. Thus, there is an urgent need for a new access control mechanism that empowers autonomous control over user identity and resources, addressing the demands for privacy-preserving authentication and flexible authorization in cross-domain scenarios.To address cross-domain access control challenges, we propose POLARIS, a unified and extensible architecture that enables policy-based, verifiable and privacy-preserving access control across different domains. POLARIS features a structured commitment mechanism for reliable, fine-grained, policy-based identity disclosure. It further introduces VPPL, a lightweight policy language that supports issuer-bound evaluation of selectively revealed attributes. A dedicated session-level security mechanism ensures binding between authentication and access, enhancing confidentiality and resilience to replay attacks.We implement a working prototype and conduct comprehensive experiments, demonstrating that POLARIS effectively provides scalable, privacy-preserving, and interoperable access control across heterogeneous domains. Our results highlight the practical viability of POLARIS for enabling secure and privacy-preserving access control in decentralized, cross-domain environments.

Approximate Nearest Neighbor (ANN) search in high-dimensional Euclidean spaces is a fundamental problem with a wide range of applications. However, there is currently no ANN method that performs well in both indexing and query answering performance, while providing rigorous theoretical guarantees for the quality of the answers. In this paper, we first design SC-score, a metric that we show follows the Pareto principle and can act as a proxy for the Euclidean distance between data points. Inspired by this, we propose a novel ANN search framework called Subspace Collision (SC), which can provide theoretical guarantees on the quality of its results. We further propose SuCo, which achieves efficient and accurate ANN search by designing a clustering-based lightweight index and query strategies for our proposed subspace collision framework. Extensive experiments on real-world datasets demonstrate that both the indexing and query answering performance of SuCo outperform state-of-the-art ANN methods that can provide theoretical guarantees, performing 1-2 orders of magnitude faster query answering with only up to one-tenth of the index memory footprint. Moreover, SuCo achieves top performance (best for hard datasets) even when compared to methods that do not provide theoretical guarantees.

Cross-border data transfer is vital for the digital economy by enabling data flow across different countries or regions. However, ensuring compliance with diverse data protection regulations during the transfer introduces significant complexities. Existing solutions either focus on a single legal framework or neglect real-time and concurrent processing demands, resulting in incomplete and inconsistent compliance management. To address this issue, we propose Cross-Border Compliance Management System (CBCMS), which not only enables the unified management of data processing policies across multiple jurisdictions to ensure compliance with various legal frameworks involved in cross-border data transfer, but also supports real-time and high-concurrency processing capabilities. We design Policy Definition Language (PDL) that supports the unified management of data processing policies, bridging the gap between natural language policies and machine-processable expressions, thereby allowing various legal frameworks to be seamlessly integrated into CBCMS. We present Compliance Policy Generation Model (CPGM), the core component of CBCMS, which generates compliant data processing policies with high accuracy, achieving up to 25.16% improvement in F1 score (reaching 97.32%) compared to rule-based baseline. CPGM achieves inference time in the order of milliseconds (6 to 13 ms), and keeps low latency even under high-load scenarios, demonstrating high real-time and concurrent performance. To our knowledge, CBCMS is the first system to support unified compliance management across jurisdictions while ensuring real-time and concurrent processing capabilities.

Domain Name System (DNS) is the backbone of the Internet infrastructure, converting human-friendly domain names into machine-processable IP addresses. However, DNS remains vulnerable to various security threats, such as cache poisoning attacks , where malicious attackers inject false information into DNS resolvers’ caches. Although efforts have been made to enhance DNS against such vulnerabilities, existing countermeasures often fall short in one or more areas: they may offer limited resistance to the collusion attack, introduce significant overhead, or require complex implementation that hinders widespread adoption. To address these challenges, this paper introduces TI-DNS+, a trusted and incentivized blockchain-based DNS resolution architecture for cache poisoning defense. TI-DNS+ introduces a Verification Cache exploiting blockchain ledger’s immutable nature to detect and correct forged DNS responses . The architecture also incorporates a multi-resolver Query Vote mechanism, enhancing the ledger’s credibility by validating each record modification through a stake-weighted algorithm. This algorithm selects resolvers as validators based on their stake proportion. To promote well-behaved participation, TI-DNS+ also implements a novel stake-based incentive mechanism that optimizes the generation and distribution of stake rewards. This ensures that incentives align with participants’ contributions, achieving incentive compatibility, fairness, and efficiency. Moreover, TI-DNS+ possesses high practicability as it requires only resolver-side modifications to current DNS. Finally, through comprehensive prototyping and experimental evaluations, the results demonstrate that our solution effectively mitigates DNS cache poisoning. Compared to competitors, our solution improves attack resistance by 1-3 orders of magnitude, while also reducing resolution latency by 5% to 68%.

Locality-sensitive hashing (LSH) is a well-known solution for approximate nearest neighbor (ANN) search in high-dimensional spaces due to its robust theoretical guarantee on query accuracy. Traditional LSH-based methods mainly focus on improving the efficiency and accuracy of the query phase by designing different query strategies, but pay little attention to improving the efficiency of the indexing phase. They typically fine-tune existing data-oriented partitioning trees to index data points and support their query strategies. However, their strategy to directly partition the multi-dimensional space is time-consuming, and performance degrades as the space dimensionality increases. In this paper, we design an encoding-based tree called Dynamic Encoding Tree (DE-Tree) to improve the indexing efficiency and support efficient range queries based on Euclidean distance. Based on DE-Tree, we propose a novel LSH scheme called DET-LSH. DET-LSH adopts a novel query strategy, which performs range queries in multiple independent index DE-Trees to reduce the probability of missing exact NN points, thereby improving the query accuracy. Our theoretical studies show that DET-LSH enjoys probabilistic guarantees on query accuracy. Extensive experiments on real-world datasets demonstrate the superiority of DET-LSH over the state-of-the-art LSH-based methods on both efficiency and accuracy. While achieving better query accuracy than competitors, DET-LSH achieves up to 6x speedup in indexing time and 2x speedup in query time over the state-of-the-art LSH-based methods.

Data has become a valuable resource that drives new business models and creates enormous business value. However, under the current data ownership model, many data-driven applications arbitrarily collect and overuse user data for commercial purposes, resulting in increased incidents of data breaches and data misuse. In this paper, we present Data Interoperating Architecture (DIA) that decouples applications and user data to give back data ownership to users. We design Data Interoperating System (DIS) based on blockchain, identity system, and identifier system to solve the key issues of data interoperation: identity management, data identification, data discovery, and data ownership protection. DIS provides services without collecting or accessing data, keeping data under the control of its owner. We formalize the interactions among components in DIA as Data Interoperating Protocol (DIP), which facilitates applications and personal data stores to be compatible with DIS. We develop a prototype of DIS and evaluate the system performance under adopted techniques. Experimental results show that DIS is effective and efficient in supporting real-world data interoperation.

The dispersion of resource authorization across various authorization systems raises the complexity and inconsistency of authorization management. Therefore, the pursuit of a unified resource authorization management system is necessary. Most widely used authorization systems are based on centralized services with a single delegation pattern. These authorization systems can be easily compromised, leading to permissions tampering, and are unsuitable for complex usage scenarios. We propose a decentralized authorization system that provides flexible delegation called FlexAuth. We first define a decentralized data storage layer based on blockchain, using smart contracts to implement data writing and resolving, preventing data from being tampered with. On top of this, we implement active and passive delegation patterns of authorization services. We allow users to delegate permissions actively. Also, FlexAuth enables them to respond to authorization requests passively by making flexible and expressive access control policies based on relation-ships and attributes, using the proposed Hybrid Access Control Model (HACM). Furthermore, all delegations in FlexAuth are transitive. Finally, through analysis and experiments, we validate the usability and efficiency of FlexAuth. To our knowledge, FlexAuth is the first decentralized authorization system with transitive delegation in active and passive patterns, achieving flexible delegation.

Domain Name System (DNS) is a critical component of the Internet infrastructure, responsible for translating domain names into IP addresses. However, DNS is vulnerable to some malicious attacks, including DNS cache poisoning, which redirects users to malicious websites displaying offensive or illegal content. Existing countermeasures often suffer from at least one of the following weakness: weak attack resistance, high overhead, or complex implementation. To address these challenges, this paper presents TI-DNS, a blockchain-based DNS resolution architecture designed to detect and correct the forged DNS records caused by the cache poisoning attacks in the DNS resolution process. TI-DNS leverages a multi-resolver Query Vote mechanism to ensure the credibility of verified records on the blockchain ledger and a stake-based incentive mechanism to promote well-behaved participation. Importantly, TI-DNS is easy to be adopted as it only requires modifications to the resolver side of current DNS infrastructure. Finally, we develop a prototype and evaluate it against alternative solutions. The result demonstrates that TI-DNS effectively and efficiently solves DNS cache poisoning.