Simple prompts to Llama 3.2 1B produce text that resembles PII, but the paper does not establish that this text is memorized training data.
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
REJECT 1representative citing papers
citing papers explorer
-
Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models
Simple prompts to Llama 3.2 1B produce text that resembles PII, but the paper does not establish that this text is memorized training data.