Medical records could be revealed by AI training-data vulnerability
About this episode
This episode discusses the vulnerabilities in AI training data that could expose sensitive medical information.
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 episodes of Nature Podcast
- Briefing Chat: Sweet! Elusive sugar molecules found in space
- ‘Holy grail’ of naked mole-rat research reveals how queens rule
- Briefing Chat: The 30 year-legacy of a science icon – Dolly the sheep
- Nukes in space? Orbital detector could sniff out warheads
- Togetherness: How co-operation built the world
- Audio long read: Is the peptide craze backed by science? The promise behind the hype
Explore listener stats, chart rankings, contacts and more on the Nature Podcast podcast page.