A Simple and Agile Cloud Infrastructure to Support Cybersecurity Oriented Machine Learning Workflows
This addresses dataset generation problems for cybersecurity researchers and practitioners, but it appears incremental as it focuses on infrastructure improvements rather than novel ML methods.
The paper tackles the challenge of generating up-to-date, well-labeled datasets for cybersecurity machine learning models by proposing a simple and resilient cloud infrastructure, which enhanced the speed of researching and maintaining multiple security ML models in production.
Generating up to date, well labeled datasets for machine learning (ML) security models is a unique engineering challenge, as large data volumes, complexity of labeling, and constant concept drift makes it difficult to generate effective training datasets. Here we describe a simple, resilient cloud infrastructure for generating ML training and testing datasets, that has enhanced the speed at which our team is able to research and keep in production a multitude of security ML models.