{
  "id": 4895,
  "url": "https://arxiv.org/abs/2605.05340v2",
  "title": "How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study",
  "summary": "As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments becomes critical. Unlike digital chatbots, these agents operate in intimate spaces, such as homes and hospitals, where they possess the physical agency to observe and manipulate privacy-sensitive information and artifacts. However, current benchmarks remain limited to unimodal, text-based representations that cannot capture ",
  "authors": "Junran Wang, Xinjie Shen, Zehao Jin, Pan Li",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-06T18:10:51.000Z",
  "fetched_at": "2026-07-14T16:31:21.932Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4895",
  "original_url": "https://arxiv.org/abs/2605.05340v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}