A Survey of Data Security: Practices from Cybersecurity and Challenges of Machine Learning

TL;DR

This survey reviews data security practices in cybersecurity and machine learning, highlighting challenges and solutions like cryptography, privacy, and federated learning to secure ML systems.

Contribution

It provides a comprehensive overview of security techniques from both cybersecurity and ML domains to foster shared understanding and future advancements.

Findings

Identifies key security challenges in ML systems

Summarizes cryptography and privacy-preserving techniques

Highlights the importance of interdisciplinary collaboration

Abstract

Machine learning (ML) is increasingly being deployed in critical systems. The data dependence of ML makes securing data used to train and test ML-enabled systems of utmost importance. While the field of cybersecurity has well-established practices for securing information, ML-enabled systems create new attack vectors. Furthermore, data science and cybersecurity domains adhere to their own set of skills and terminologies. This survey aims to present background information for experts in both domains in topics such as cryptography, access control, zero trust architectures, homomorphic encryption, differential privacy for machine learning, and federated learning to establish shared foundations and promote advancements in data security.