Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Garfield introduces the GMG index and GPU pipeline for multi-attribute RFANNS, achieving 4.4x smaller indexes and 119.8x higher throughput than existing approaches.
citing papers explorer
-
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.
-
A GPU-Accelerated Framework for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search
Garfield introduces the GMG index and GPU pipeline for multi-attribute RFANNS, achieving 4.4x smaller indexes and 119.8x higher throughput than existing approaches.