{
  "id": 9055394,
  "title": "LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication",
  "url": "https://urgent.news/2026/09/19/llms-as-linguistic-chameleons-decoupling-semantics-and-structure-for",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-19T19:41:29.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.23193v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}