Privacy-Preserving Machine Learning [Cryptography]

Florian Kerschbaum, Nils Lukas

Abstract: Privacy challenges in machine learning can stem from leakage by the model or from distributed data sources. Differential privacy addresses model leakage and computation over encrypted data the other. During training cryptographic approaches need to be augmented with techniques such as federated learning.

External IDs:doi:10.1109/msec.2023.3315944