Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects

arXiv:2604.05480 · cs.CR, cs.DB · Submitted 2026-04-07 · Read on arXiv

cs.CR, cs.DB

Submitted: 2026-04-07

Updated: 2026-10-20

Comments: Accepted by VLDB2027. Source code: https://github.com/hanxi19/Black_Hole_Attack_for_Vector_Database

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills