Published June 26, 2022 | Version v1
Poster Open

Challenges Of Using Homomorphic Encryption In Machine Learning

Creators

  • 1. university of Luxembourg

Description

In recent years, homomorphic encryption has been widely studied as a privacy enhancing technology to be applied in machine learning. Despite the strong security guarantees, this adoption faces many challenges that are discussed in this poster.

Files

Poster_Crete_ppml_Soumia_Zohra_ElMestari (6).pdf

Files (466.5 kB)

Name Size Download all
md5:f1b66264fb0dfe21813aa61dea90acc8
466.5 kB Preview Download

Additional details

Funding

European Commission
LeADS - Legality Attentive Data Scientists 956562

References

  • J. H. Cheon, A. Kim, M. Kim, and Y. Song. Homomorphic encryption for arithmetic of approximate numbers. In International Conference on the Theory and Application of Cryptology and Information Security, pages 409–437. Springer, 2017.
  • R. Gilad-Bachrach, N. Dowlin, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In International conference on machine learning, pages 201–210. PMLR, 2016.
  • P. Martins, L. Sousa, and A. Mariano. A survey on fully homomorphic encryption: An engineering perspective. ACM Computing Surveys (CSUR), 50(6):1–33, 2017