Medical records could be revealed by AI training-data vulnerability

In this episode:00:46 How sensitive information can be gleaned from medical AIsResearch 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 HighlightsNature: A long-lived butterfly’s secret to graceful ageingNature: It slices! It dices! Sashimi-Bot handles seafood with ease13:57 Across the Universe, galaxies clump together more than physicists thought they shouldResearch article: Labini & GaloppoSubscribe 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.