What question did this study set out to answer?

January 1, 2022IEEE AccessOpen Access

A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption

View Full Paper

Ask AI

Bookmark

The aim is to review deep learning architectures for privacy-preserving machine learning that utilize fully homomorphic encryption.
Reviewed scientific articles on privacy-preserving machine learning and homomorphic encryption.
Analyzed neural network architecture changes for compatibility with homomorphic encryption.
Discussed potential solutions for challenges associated with homomorphic encryption in deep learning.
Identified challenges including computational overhead and usability in homomorphic encryption-based privacy-preserving solutions.
Proposed new evaluation metrics for comparing different privacy-preserving machine learning solutions.

No takes yet. Share an insight, caveat, or question.

Survey analyzes privacy-preserving deep learning solutions using homomorphic encryption, highlighting challenges and evaluation metrics.

Podschwadt et al. (2022) studied this question.

View Full Paper

Ask AI

Bookmark