A Principled Approach to Enriching Security-related Data for Running Processes through Statistics and Natural Language Processing

We propose a principled method of enriching security related information for running processes. Our methodology applies to large organizational infrastructures, where information is properly collected and stored. The data we use is based on the Hubble Stack (an open-source project), but any alternative solution that provides the same type of information will suffice. Using statistical and natural language processing (NLP) methods we enrich our data with tags and we provide an analysis on how these tags can be used in Machine Learning approaches for anomaly detection.