arXiv (All)
open access
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
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 att
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects#2761
- (A)iSpy: Parasitic Trojans for Machine Learning Infrastructure#386779
- Machine Learning-Powered Anomaly Detection: Enhancing Data Security and Integrity#328753
- Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning#133941
- Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks#1011532
Record · ID 1403072
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive