Episode

Medical records could be revealed by AI training-data vulnerability

Podcast
Nature Podcast
Published
Jun 24, 2026
Duration seconds
1194
Processing state
not_requested
Canonical source
https://www.nature.com/articles/d41586-026-02032-3
Audio
https://sphinx.acast.com/p/acast/s/nature/e/6a3bee5feeb75ff76e1e4084/media.mp3
JSON
/v1/public/podcasts/nature-podcast-836788/episodes/medical-records-could-be-revealed-by-ai-training-data-vulnerability
Markdown
/podcast/nature-podcast-836788/medical-records-could-be-revealed-by-ai-training-data-vulnerability.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/nature-podcast-836788/episodes/medical-records-could-be-revealed-by-ai-training-data-vulnerability/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/nature-podcast-836788/medical-records-could-be-revealed-by-ai-training-data-vulnerability.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

In this episode: 00:46 How sensitive information can be gleaned from medical AIs Research article: Knolle et al. Correction: The story about medical AI-data privacy incorrectly stated that the number of individuals at high risk of a membership inference attack increases as training-dataset size grows. It should have stated that the increase in risk occurs when the AI model increases in capacity and size. 11:31 Research Highlights Nature: A long-lived butterfly’s secret to graceful ageing Nature: It slices! It dices! Sashimi-Bot handles seafood with ease 13:57 Across the Universe, galaxies clump together more than physicists thought they should Research article: Labini & Galoppo Subscribe to Nature Briefing, an unmissable daily round-up of science news, opinion and analysis free in your inbox every weekday. Hosted on Acast. See acast.com/privacy for more information.