Skip to content

Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption

Authors: R. Geva; A. Gusev; Y. Polyakov; L. Liram; O. Rosolio; A. Alexandru; N. Genise; M. Blatt; Z. Duchin; B. Waissengrin; D. Mirelman; F. Bukstein; D. T. Blumenthal; I. Wolf; S. Pelles-Avraham; T. Schaffer; L. A. Lavi; D. Micciancio; V. Vaikuntanathan; A. A. Badawi; S. Goldwasser
Year: 2023

type: application collection: sok-references status: auto

Links: ePrint 2023/1203

Summary

Auto-extracted summary (unreviewed)

This work builds a toolset for collaborative privacy-preserving analysis of oncological real-world data using multiparty (threshold) CKKS FHE implemented in PALISADE, covering descriptive statistics, survival analysis and logistic regression training, together with a private join-and-compute component and a new interactive bootstrapping protocol for multiparty FHE. The authors report high accuracy and practical performance that scales to larger data sets, though the excerpt contains no concrete numbers.

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. 1 Contents
Source: pdf

Extracted details

Field Value Source Confidence
contribution multiparty FHE toolset for collaborative oncological data analysis llm 0.70
contribution support for descriptive statistics, survival analysis and logistic regression training llm 0.70
contribution novel interactive bootstrapping protocol for multiparty FHE llm 0.70
contribution private join-and-compute and multiparty setup procedures llm 0.70
contribution evaluation on real oncological data sets llm 0.70
schemes CKKS llm 0.70
schemes threshold / multiparty FHE llm 0.70
libraries PALISADE llm 0.70
models logistic regression llm 0.70
datasets oncological real-world data sets llm 0.70
tasks survival analysis llm 0.70
tasks logistic regression training llm 0.70
tasks descriptive statistics llm 0.70
tasks healthcare data analytics llm 0.70
security level 128-bit llm 0.70
threat model multiparty data owners with threshold decryption llm 0.70
interaction interactive (HE+MPC) llm 0.70
code url https://gitlab.com/palisade/palisade-releasehttps (URL found in the full text) regex 0.50

SoK reference [7]

R. Geva, A. Gusev, Y. Polyakov, L. Liram, O. Rosolio, A. Alexandru, N. Genise, M. Blatt, Z. Duchin, B. Waissengrin, D. Mirelman, F. Bukstein, D. T. Blumenthal, I. Wolf, S. Pelles-Avraham, T. Schaffer, L. A. Lavi, D. Micciancio, V. Vaikuntanathan, A. A. Badawi, and S. Goldwasser, “Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption,” Proceedings of the National Academy of Sciences, vol. 120, no. 33, p. e2304415120, 2023. [Online]. Available: https://www.pnas.org/doi/abs/10.1073/pnas.2304415120

Listed on the reference page of the site.

Keyword mentions

Counts of vocabulary terms in the full text (first page of occurrence in brackets).

  • scheme: CKKS 35 [p.2], Secret sharing 22 [p.3], MPC 21 [p.3], Threshold HE 14 [p.6], BFV 13 [p.9], Multiparty HE 3 [p.1]
  • library: PALISADE 10 [p.13]
  • model: Logistic regression 33 [p.1], CNN 2 [p.4], ResNet 1 [p.4]
  • dataset: CIFAR-10 1 [p.4]
  • hardware: Intel Xeon 2 [p.14]
  • technique: Bootstrapping 69 [p.1], Sigmoid 16 [p.4], RNS 12 [p.13], Two-party computation 11 [p.2], Semi-honest model 8 [p.13], Chebyshev 7 [p.4], Rotations 7 [p.12], Key switching 5 [p.14], Rescaling 5 [p.14], SIMD packing 4 [p.23], Non-interactive 4 [p.3], Polynomial approximation 3 [p.4], NTT 3 [p.23], Lookup table 3 [p.39], Relinearization 2 [p.24], Matrix multiplication 2 [p.56], Convolution 2 [p.18]
  • assumption: DDH 52 [p.12], RLWE 12 [p.23], Lattice-based 6 [p.3], LWE 2 [p.19], Post-quantum 2 [p.12]
  • task: Medical / healthcare 90 [p.1], Genomics 17 [p.3]
  • topic: Homomorphic encryption 151 [p.1], Open source 3 [p.13], Benchmark 2 [p.59]

Files

Path (under papers/) Collection Pages Size SHA-256 Note
references/sok-references/007_collaborative-privacy-preserving-analysis-of-oncological-dat.pdf sok-references 63 1.7 MB a441a1d58bf4

Database key: collaborative-privacy-preserving-analysis-of-oncological-data-using · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set collaborative-privacy-preserving-analysis-of-oncological-data-using COLUMN VALUE