Machine Learning String Tools for Operational and Network Security
Principal Investigator: C Oehmen
Technical Advisor: G Fink, Adaptive Systems Focus Area
Purpose of research
- Provide capability framework for rapidly developing new text-based characterization applications in cyber domains
- Provide a pattern-matching approach to complement or augment current rule-based approaches in cybersecurity
Key idea
Digital data is analogous to biological sequences. Let's exploit biosequence theory to provide rigorous and repeatable framework to augment cybersecurity.
Discriminator
Discriminator for this R&D is that it does not rely on rule-based approaches. This approach enables more rapid evolution of defense strategies to help keep pace with evolving threat.
Summary
Machine Learning String Tools for Operational and Network Security (MLSTONES) is a collection of methods for characterizing text-based strings from various cyber applications using biological sequence analysis theory and machine learning to extract patterns.