Tab-MIA shows LLMs fine-tuned on tabular data are vulnerable to membership inference attacks, with AUROC up to 97.7% after three epochs and encoding format strongly affecting leakage.
Tag&tab: Pretraining data detection in large language models using keyword-based membership inference attack
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
Tab-MIA shows LLMs fine-tuned on tabular data are vulnerable to membership inference attacks, with AUROC up to 97.7% after three epochs and encoding format strongly affecting leakage.