Medical records could be revealed by AI training-data vulnerability
From Nature Podcast · · 19 min
This plays from the publisher's own server. We do not host a copy.
Description
In this episode:
00:46 How sensitive information can be gleaned from medical AIs
Research article: Knolle et al. (https://www.nature.com/articles/s41586-026-10688-0)
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 (https://www.nature.com/articles/d41586-026-01948-0)
Nature: It slices! It dices! Sashimi-Bot handles seafood with ease (https://www.nature.com/articles/d41586-026-01871-4)
13:57 Across the Universe, galaxies clump together more than physicists thought they should
Research article: Labini & Galoppo (https://www.nature.com/articles/s41586-026-10702-5)
Subscribe to Nature Briefing, an unmissable daily round-up of science news, opinion and analysis free in your inbox every weekday. (https://www.nature.com/briefing/signup)
Hosted on Acast. See acast.com/privacy (https://acast.com/privacy) for more information.