arXiv cs.CL
· Papers
Where Privacy Risk Lives in English-Source Multilingual RAG: A Stage-Decomposed Audit Across Five Query Languages
arXiv:2608.05163v1 Announce Type: new Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information. We test this on an English-source synthetic-PII corpus with five query languages and a two-stage defence (LLM input judge + regex