Can You Trust The Vectors In Your Vector Database? Black-hole Attack From Embedding Space Defects

Abstract

Vector databases serve as the retrieval backbone of modern AI applications, yet their security remains largely unexplored. We propose the Black-Hole Attack, a poisoning attack that injects a small number of malicious vectors near the geometric center of the stored vectors. These injected vectors attract queries like a black hole and frequently appear in the top-k retrieval results for most queries. This attack is enabled by a phenomenon we term centrality-driven hubness: in high-dimensional embedding spaces, vectors near the centroid become nearest neighbors of a disproportionately large number of other vectors, while this centroid region is nearly empty in practice. The attack shows that vectors in a vector database cannot be blindly trusted: geometric defects in high-dimensional embeddings make retrieval inherently vulnerable. Our experiments show that malicious vectors appear in up to 99.85% of top-10 results. Additionally, we evaluate existing hubness mitigation methods as potentia

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2026can

Related papers

• Breaking The Curse Of Dimensionality: On The Stability Of Modern Vector Retrieval (2025)0.00
• Adversarial Hubness In Multi-modal Retrieval (2024)0.00
• Semantic Certainty Assessment In Vector Retrieval Systems: A Novel Framework For Embedding Quality Evaluation (2025)0.00
• Reveal Hidden Pitfalls And Navigate Next Generation Of Vector Similarity Search From Task-centric Views (2025)0.00
• On The Theoretical Limitations Of Embedding-based Retrieval (2025)0.00
• On Strengths And Limitations Of Single-vector Embeddings (2026)0.00
• Vector Database Management Systems: Fundamental Concepts, Use-cases, And Current Challenges (2023)14.23
• Understanding And Mitigating The Threat Of Vec2text To Dense Retrieval Systems (2024)7.16