NEWS AND VIEWS04 August 2026Privacy attacks can reveal whether someone’s medical data was used to train an AI model. People who differ from the majority are the most vulnerable to such attacks.ByHaoran Zhang0 &Marzyeh Ghassemi1Haoran ZhangHaoran Zhang is in the Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.View author publicationsSearch author on: PubMed Google ScholarMarzyeh GhassemiMarzyeh Ghassemi is in the Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.View author publicationsSearch author on: PubMed Google ScholarThe 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 Access through your institutionAccess Nature and 54 other Nature Portfolio journalsGet Nature+, our best-value online-access subscription27,99 € / 30 dayscancel any timeLearn moreSubscribe to this journalReceive 52 print issues and online access199,00 € per yearonly 3,83 € per issueLearn moreRent or buy this articlePrices vary by article typefrom$1.95to$39.95Learn morePrices may be subject to local taxes which are calculated during checkoutNature 656, 42-44 (2026)doi: https://doi.org/10.1038/d41586-026-02288-9ReferencesKnolle, M. A. et al. Nature 656, 192–198 (2026).Article Google Scholar 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).Google Scholar Gichoya, J. W. et al. Lancet Digit. Health 4, E406–E414 (2022).Article PubMed Google Scholar 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).Download referencesCompeting InterestsThe authors declare no competing interests. Read the paper: Disparate privacy risks from medical AI People are turning to AI chatbots to plug gaps in health information A hidden predictor of sudden cardiac death uncovered by deep learningSee all News & ViewsSubjectsMachine learningSocietyHealth careInformation technologyLatest on:Machine learningSocietyHealth careJobs Group Leader - Neural Circuit Regulation of Immune FunctionWhat we are looking for The BioMed X Institute in New Haven, Connecticut, USA is establishing a new, fully funded research group in the following f...New Haven, Connecticut, USABioMed X Germany GmbHAssociate Editor, Discover Journals (Materials Science)Job Title: Associate Editor, Discover Journals (Materials Science) Location: Singapore, Shanghai, Beijing, Nanjing or Pune, Hybrid Working Mo...Singapore, Shanghai, Beijing, Nanjing or Pune, Hybrid Working ModelSpringer Nature LtdPostdoctoral Fellowships WorldwideIBSA Foundation for scientific research offers 7 fellowships of € 32.000 to young researchers under 40 years.The call is open to people from research institutes and universities from all over the world.IBSA Foundation for scientific research