Paper 2021/733

GenoPPML – a framework for genomic privacy-preserving machine learning

Sergiu Carpov, Nicolas Gama, Mariya Georgieva, and Dimitar Jetchev


We present a framework GenoPPML for privacy-preserving machine learning in the context of sensitive genomic data processing. The technology combines secure multiparty computation techniques based on the recently proposed Manticore secure multiparty computation framework for model training and fully homomorphic encryption based on TFHE for model inference. The framework was successfully used to solve breast cancer prediction problems on gene expression datasets coming from distinct private sources while preserving their privacy - the solution winning 1st place for both Tracks I and III of the genomic privacy competition iDASH'2020. Extensive benchmarks and comparisons to existing works are performed. Our 2-party logistic regression computation is $11\times$ faster than the one in De Cock et al. on the same dataset and it uses only a single CPU core.

Available format(s)
Publication info
Preprint. MINOR revision.
privacy-preserving machine learningmulti-party computationhomomorphic encryptiongenomic privacydifferential privacy
Contact author(s)
sergiu @ inpher io
nicolas @ inpher io
mariya @ inpher io
dimitar @ inpher io
2021-12-06: revised
2021-06-03: received
See all versions
Short URL
Creative Commons Attribution


      author = {Sergiu Carpov and Nicolas Gama and Mariya Georgieva and Dimitar Jetchev},
      title = {GenoPPML – a framework for genomic privacy-preserving machine learning},
      howpublished = {Cryptology ePrint Archive, Paper 2021/733},
      year = {2021},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.