The use of artificial-intelligence tools in medicine has hinged on an implicit bargain. Patients and health systems permit sensitive records to be used for research, usually after de-identification so that names and other pieces of personal information are removed. In return, researchers and developers create tools that could improve health care, for example by enabling earlier diagnoses and new treatments. This bargain relies on the assumption that it is impossible for people who have access to an AI model to infer information about individuals whose data were used to train it. Writing in Nature, Knolle et al.1 show that, in the context of powerful machine-learning models, this assumption is often untrue.
Access options
Prices may be subject to local taxes which are calculated during checkout
doi: https://doi.org/10.1038/d41586-026-02288-9
References
-
Knolle, M. A. et al.Nature656, 192–198 (2026).
-
Feldman, V. & Chiyuan, Z. In Proc. 34 Int. Conf. Neural Inf. Process. Syst. (eds Larochelle, H. et al.) 2881–2891 (Curran Associates, 2020).
-
Tonekaboni, S., Stempfle, L., Fallahpour, A., Gerych, W. & Ghassemi, M. In Adv. Neural Inf. Process. Syst. 39 (eds Belgrave, D. et al.) 10555–10580 (2026).
-
Geiping, J., Bauermeister, H., Dröge, H. & Moeller, M. In Proc. 34 Int. Conf. Neural Inf. Process. Syst. (eds Larochelle, H. et al.) 16937–16947 (Curran Associates, 2020).
-
Chen, M. et al. In Proc. 2021 ACM SIGSAC Conf. Comput. Commun. Secur. 896–911 (ACM, 2021).
-
Shokri, R., Stronati, M., Song, C. & Shmatikov, V. In Proc. 2017 IEEE Symp. Secur. Priv. (ed. O’Conner, L.) 3–18 (IEEE, 2017).
-
Nissenbaum, H. Wash.Law Rev.79, 119–157 (2004).
-
Gichoya, J. W. et al.Lancet Digit. Health4, E406–E414 (2022).
-
Abadi, M. et al. In Proc. 2016 ACM SIGSAC Conf. Comput. Commun. Secur. 308–318 (ACM, 2016).
-
Suriyakumar, V. M., Papernot, N., Goldenberg, A. & Ghassemi, M. In Proc. 2021 ACM Conf. Fairness Account. Transpar. 723–734 (ACM, 2021).
Competing Interests
The authors declare no competing interests.
Subjects
Latest on:
- Machine learning
- Society
- Health care
Want to get more from AI? Treat every prompt like an experiment
-
Scientists using LLMs will ‘do more, less well’, modelling study predicts
-
This AI Raygun can shrink and supersize proteins — opening the door to easy editing
-
Scientists don’t need more trust, they need public allies
-
How I use statistics and my law degree to fight human-rights abuses
-
New-deal mortgage programmes benefited white borrowers disproportionately
-
Put health systems at the centre of European heatwave plans
-
Why the need for the WHO has never been greater
-
Europe can become a bioengineering powerhouse with these three changes
