Prof. Jean-Pierre Hubaux
Academic Director of C4DT.org, EPFL
1st November 2022, 1:00pm - 2:00pm (GST)
Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption
Using real-world evidence in biomedical research, an indispensable complement to clinical trials, requires access to large quantities of patient data that are typically held separately by multiple healthcare institutions. We propose FAMHE, a novel federated analytics system that, based on multiparty homomorphic encryption (MHE), enables privacy-preserving analyses of distributed datasets by yielding highly accurate results without revealing any intermediate data. We demonstrate the applicability of FAMHE to essential biomedical analysis tasks, including Kaplan-Meier survival analysis in oncology and genome-wide association studies in medical genetics. Using our system, we accurately and efficiently reproduce two published centralized studies in a federated setting, enabling biomedical insights that are not possible from individual institutions alone. Our work represents a necessary key step towards overcoming the privacy hurdle in enabling multi-centric scientific collaborations. In the talk, we will also explain how we made use of this technique to enable privacy-preserving federated neural network learning for disease-associated cell classification.
Through his research, Prof. Jean-Pierre Hubaux contributes to laying the foundations and developing the tools for protecting privacy in today’s hyper-connected world. He has pioneered the areas of privacy and security in mobile/wireless networks and in personalized health. He is the academic director of the EPFL Center for Digital Trust (C4DT.org). Until December 2021, he led the Data Protection in Personalized Health (DPPH) project funded by the ETH Council and was co-chair of the Data Security Work Stream of the Global Alliance for Genomics and Health (GA4GH). He is a Fellow of both IEEE (2008) and ACM (2010). Recent awards: three of his papers obtained distinctions at the IEEE Symposium on Security and Privacy in 2015, 2018 and 2021. He is among the most cited researchers in privacy protection and in information security. He is a co-founder of Tune Insight SA,