PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
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.
citing papers explorer
-
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
-
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.