LLM tabular generators leak memorized numeric strings, allowing a no-box attack to achieve near-perfect membership inference on some state-of-the-art models.
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
roles
background 1polarities
background 1representative citing papers
The skd-tree partitions space into multiple slices per node along one dimension, compresses splitters, and applies a constant number of SIMD instructions per node to reduce levels and computations for multi-dimensional queries.
citing papers explorer
-
When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation
LLM tabular generators leak memorized numeric strings, allowing a no-box attack to achieve near-perfect membership inference on some state-of-the-art models.
-
In-memory Multidimensional Indexing Using the skd-tree
The skd-tree partitions space into multiple slices per node along one dimension, compresses splitters, and applies a constant number of SIMD instructions per node to reduce levels and computations for multi-dimensional queries.