Nature Podcast

Medical records could be revealed by AI training-data vulnerability

Nature Podcast

Show Notes

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.

More from Nature Podcast

Oct 19, 2026

Critical thinking is a skill that is under threat from the AI revolution in large language models. But all is not lost. Specialists in education and cognition have long been studying critical thinking, and some have useful tips on how to stay cognitively sharp in the age of AI.

Oct 14, 2026

Analysis suggests number of protected areas is hugely underestimated but biodiversity is still in peril — plus, a huge study looking at the health effects of brown fat. 00:45 The world may have more conservation areas than previously thought Research Article: O’Neill et al.

Oct 9, 2026

In this episode we discuss a recent Nature exclusive investigating an international constellation of sham academies and societies that have successfully misled some of the world’s leading scientists and universities. Nature: Exclusive: Sham scientific societies are misleading star researchers

See all episodes →