Machine Learning and Pattern Recognition on Encrypted Medical and Bioinformatics Data

Lecture / Panel
For NYU Community

Image of Data Tree


Delaram Kahrobaei, PhD
Professor, Depts. of Mathematics and Computer Science
City University of New York (CCNY)
Honorary Chair of Cybersecurity, University of York (UK)


Machine learning and statistical techniques are powerful tools for analyzing large amounts of medical and genomic data. On the other hand, ethical concerns and privacy regulations prevent free sharing of this data. Encryption techniques such as fully homomorphic encryption (FHE) enable evaluation over encrypted data. Using FHE, machine learning models such as deep learning, decision trees, and Naive Bayes have been implemented for privacy-preserving applications using medical data. These applications include classifying encrypted data and training models on encrypted data. FHE has also been shown to enable secure genomic algorithms, such as paternity and ancestry testing and privacy-preserving applications of genome-wide association studies.  I will give a survey an overview of fully homomorphic encryption and its applications in medicine and bioinformatics. The high-level concepts behind FHE and its history will be introduced, and details on current open-source implementations will be provided. The state of fully homomorphic encryption for privacy-preserving techniques in machine learning and bioinformatics will be reviewed, along with descriptions of how these methods can be implemented in the encrypted domain. 

Dr. Kahrobaei received a MS degree in Applied Mathematics from the Claremont Colleges in California and a MA in Computer Science from the City College of New York (CCNY). She went on to pursue a PhD degree in Mathematics from the City University in New York (CUNY) and subsequently held various Visiting and Assistant Professorships around the world, including the Univ. of Geneva, Switzerland, the Institut des Hautes Études Scientifiques and the Institut Henri-Poincare, France, University of St. Andrews, Scotland. During this time, she established herself as a leader in the field of cryptology and cybersecurity. In 2015 she was appointed Professor of Mathematics and Computer Science at CUNY. In 2018 she accepted an offer from the Univ. of York, England, to become the Founding Director of the Interdisciplinary Center for Cybersecurity. She is currently one of the External Advisors of the NSF funded Accelerating impact through Partnerships, Center for Data Driven Drug Development and Treatment Assessment (DATA) at University of Michigan. Her research has been funded among others by DoD, NSF, and AAAS.

Image of data being encrypted
Under an additive homomorphism, encryption followed by homomorphic addition is equal to addition followed by encryption.