A Review of Machine Learning and Cryptography Applications
Korn Sooksatra, Pablo Rivas · 2020
Adversarially robust neural cryptography deals with the training of a neural-based model using an adversary to leverage the learning process in favor of reliability and trustworthiness. The adversary can be a neural network or a strategy guided by a neural network. These mechanisms are proving successful in finding secure means of data protection. Similarly, machine learning benefits significantly from the cryptography area by protecting models from being accessible to malicious users. This paper is a literature review on the symbiotic relationship between machine learning and cryptography. We explain cryptographic algorithms that have been successfully applied in machine learning problems and, also, deep learning algorithms that have been used in cryptography. We pay special attention to the exciting and relatively new area of adversarial robustness.