A random forest trained on transformer hidden-state and attention features detects training data membership with about 0.83 average AUC, far above output-based attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis
A random forest trained on transformer hidden-state and attention features detects training data membership with about 0.83 average AUC, far above output-based attacks.