Textual data is often represented as realnumbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddings can be vulnerable to security breaches, as research shows that text can be reconstructed from embeddings, even without knowledge of the underlying model. While defence mechanisms have been explored, these are exclusively focused on English, leaving other languages vulnerable to attacks. This work explores LLM security through multilingual embedding inversion. We define the problem of black-box multilingual and cross-lingual inversion attacks, and thoroughly explore their potential implications. Our findings suggest that multilingual LLMs may be more vulnerable to inversion attacks, in part because English based defences may be ineffective. To alleviate this, we propose a simple masking defense effective for both monolingual and multilingual models. This study is the first to investigate multilingual inversion attacks, shedding light on the differences in attacks and defenses across monolingual and multilingual settings.

翻译：暂无翻译