一句话：提出首个面向向量数据库管理系统的模糊测试框架 VDBFuzz，通过边界值测试发现崩溃缺陷。
向量数据库管理系统（VDBMS）在 LLM 应用中日益关键，但其高维数据结构、多样索引和异构实现带来可靠性风险。边界条件失败（如非法配置、维度不匹配）引发的崩溃缺陷可导致数据丢失、索引损坏和级联故障。为此，本文提出 VDBFuzz，首个通过边界值测试专门检测 VDBMS 崩溃缺陷的模糊测试框架，系统化收集高质量种子、生成边缘用例并探索复杂 API 交互。在 8 个代表性系统（如 Weaviate、Milvus、Faiss、pgvector）上评估，其代码覆盖率最高为 RESTler 和 Schemathesis 等 SOTA 的 3 倍，并发现 19 个未知缺陷，其中 13 个崩溃漏洞、6 个运行时异常。
Vector Database Management Systems (VDBMSs) have become critical in LLM-integrated applications. However, their inherent complexity, including high-dimensional data structures, diverse indexing strategies, and heterogeneous implementations, makes them prone to reliability issues. Among these, crash bugs caused by boundary condition failures, such as invalid configurations and mismatched data dimensions, are particularly severe. These bugs can result in serious consequences like data loss, corrupted indexes, and cascading failures. To address this gap, we propose VDBFuzz, the first fuzzing framework specifically designed to detect VDBMS crash bugs through boundary value testing. VDBFuzz systematically leverages techniques to collect high-quality seeds, generate edge-case inputs, and explore complex API interactions. We evaluated VDBFuzz on 8 representative VDBMSs, including native systems (e.g., Weaviate, Milvus), libraries (e.g., Faiss, hnswlib), and extended systems (e.g., pgvector, sqlite-vec). VDBFuzz achieved up to 3x higher code coverage compared to state-of-the-art tools such as RESTler and Schemathesis, uncovering 19 previously unknown bugs, including 13 crash vulnerabilities and 6 runtime exceptions. These results highlight VDBFuzz’s effectiveness in improving the robustness and reliability of VDBMSs.
@inproceedings{paperbot11628,
title = {VDBFuzz: Understanding and Detecting Crash Bugs in Vector Database Management Systems},
author = {Shenao Wang and Zhao Liu and Yanjie Zhao and Quanchen Zou and Haoyu Wang},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773139}
}