Paper 2023/1203

Collaborative Privacy-Preserving Analysis of Oncological Data using Multiparty Homomorphic Encryption

Ravit Geva, Tel Aviv Sorasky Medical Center
Alexander Gusev, Dana-Farber Cancer Institute, Harvard Medical School
Yuriy Polyakov, Duality Technologies
Lior Liram, Duality Technologies
Oded Rosolio, Duality Technologies
Andreea Alexandru, Duality Technologies
Nicholas Genise, Duality Technologies
Marcelo Blatt, Duality Technologies
Zohar Duchin, Duality Technologies
Barliz Waissengrin, Tel Aviv Sorasky Medical Center
Dan Mirelman, Tel Aviv Sorasky Medical Center
Felix Bukstein, Tel Aviv Sorasky Medical Center
Deborah T. Blumenthal, Tel Aviv Sorasky Medical Center
Ido Wolf, Tel Aviv Sorasky Medical Center
Sharon Pelles-Avraham, Tel Aviv Sorasky Medical Center
Tali Schaffer, Tel Aviv Sorasky Medical Center
Lee A. Lavi, Tel Aviv Sorasky Medical Center
Daniele Micciancio, University of California, San Diego, Duality Technologies
Vinod Vaikuntanathan, Massachusetts Institute of Technology, Duality Technologies
Ahmad Al Badawi, Duality Technologies
Shafi Goldwasser, Simons Institute for the Theory of Computing, University of California, Berkeley, Duality Technologies
Abstract

Real-world healthcare data sharing is instrumental in constructing broader-based and larger clinical data sets that may improve clinical decision-making research and outcomes. Stakeholders are frequently reluctant to share their data without guaranteed patient privacy, proper protection of their data sets, and control over the usage of their data. Fully homomorphic encryption (FHE) is a cryptographic capability that can address these issues by enabling computation on encrypted data without intermediate decryptions, so the analytics results are obtained without revealing the raw data. This work presents a toolset for collaborative privacy-preserving analysis of oncological data using multiparty FHE. Our toolset supports survival analysis, logistic regression training, and several common descriptive statistics. We demonstrate using oncological data sets that the toolset achieves high accuracy and practical performance, which scales well to larger data sets. As part of this work, we propose a novel cryptographic protocol for interactive bootstrapping in multiparty FHE, which is of independent interest. The toolset we develop is general-purpose and can be applied to other collaborative medical and healthcare application domains.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Published elsewhere. Proceedings of the National Academy of Sciences, 2023, Vol. 120, No. 33
DOI
10.1073/pnas.2304415120
Keywords
fully homomorphic encryptionsecure multiparty computationCKKSBFVbootstrappingmedical data analysis
Contact author(s)
ypolyakov @ dualitytech com
History
2023-08-10: approved
2023-08-08: received
See all versions
Short URL
https://ia.cr/2023/1203
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2023/1203,
      author = {Ravit Geva and Alexander Gusev and Yuriy Polyakov and Lior Liram and Oded Rosolio and Andreea Alexandru and Nicholas Genise and Marcelo Blatt and Zohar Duchin and Barliz Waissengrin and Dan Mirelman and Felix Bukstein and Deborah T. Blumenthal and Ido Wolf and Sharon Pelles-Avraham and Tali Schaffer and Lee A. Lavi and Daniele Micciancio and Vinod Vaikuntanathan and Ahmad Al Badawi and Shafi Goldwasser},
      title = {Collaborative Privacy-Preserving Analysis of Oncological Data using Multiparty Homomorphic Encryption},
      howpublished = {Cryptology {ePrint} Archive, Paper 2023/1203},
      year = {2023},
      doi = {10.1073/pnas.2304415120},
      url = {https://eprint.iacr.org/2023/1203}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.