Study reveals privacy risks in medical AI
With this setup, it would be possible, for example, to attack an AI model that uses blood test results to predict the likelihood of success of ...
Read the original at Informationsdienst Wissenschaft ↗
- Topics
- Privacy & SurveillanceHealthcare
- Tracked via
- “An AI Model that”
Same story, other outlets
- Study reveals privacy risks in medical AI - TUM TUM · Jun 30, 2026