Secure Cryptographic Techniques for Protecting Machine Learning
American Journal Of Cryptography And Network Security · 28.02.2023 · 4 (1) · 8-13
DOI: 10.71465/ajcns1018 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal Of Cryptography And Network Security, online erschienen am 28.02.2023. Verfasst von Prof. Marcus Lindström:.
Abstract (Originalsprache)
As machine learning (ML) models become increasingly central to decision in sensitive domains such as healthcare, finance, and defense, securing these models from adversarial threats is of paramount importance. Cryptographic techniques offer a foundational approach to safeguarding the confidentiality, integrity, and privacy of ML models and their data. This paper reviews and analyzes various cryptographic mechanisms including homomorphic encryption, secure multiparty computation, differential privacy, and federated learning that have been proposed or implemented to protect ML workflows. We compare the techniques based on their computational overhead, security guarantees, and deployment feasibility, aiming to offer a comprehensive guide for practitioners and researchers in both the ML and security communities.
Zitieren
APA
Lindström:, P. M. (2023). Secure Cryptographic Techniques for Protecting Machine Learning. American Journal Of Cryptography And Network Security, 4(1), 8-13. https://doi.org/10.71465/ajcns1018
Vancouver
Lindström: PM. Secure Cryptographic Techniques for Protecting Machine Learning. American Journal Of Cryptography And Network Security. 2023;4(1):8-13. doi:10.71465/ajcns1018
BibTeX
@article{Lindstrm2023,
author = {Lindström:, Prof. Marcus},
title = {Secure Cryptographic Techniques for Protecting Machine Learning},
journal = {American Journal Of Cryptography And Network Security},
year = {2023},
volume = {4},
number = {1},
pages = {8--13},
doi = {10.71465/ajcns1018}
}
EUVIMED