Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII

Excerpt

arXiv:2610.06093v1 Announce Type: cross Abstract: The robustness of Personally Identifiable Information (PII) protection in Large Language Models (LLMs) is a critical concern, yet the risks associated with cross-lingual data extraction remain under-explored. This study evaluates the vulnerability of English-centric and multilingual models to Training Data Extraction (TDE) attacks when prompted in non-English languages. We construct a multi-domain PII dataset comprising social media handles, emai