LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication

Excerpt

arXiv:2609.23193v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromising task utility remains a major challenge. Existing approaches preserve most of the original semantic content to maintain downstream performance, but this also leaves exploitable cues for reconstructing the original text. This work investigates semantic decoupling, which replaces original semantics