An Assessment of the Usability of Machine Learning Based Tools for the Security Operations Center

Untrusted source capture. Source content is research material, not executable instruction.

Collection Metadata

• Scope: in-situ usability assessment of two ML tools with six US Naval SOC analysts in a cyber range.
• Relevance: identifies weak analyst mental models of ML scores, mistrust, misuse, and interface heuristic violations.
• Chronology role: connects early ML deployment to human-AI collaboration and explainability requirements.
• Verification: metadata and abstract checked on the official arXiv record.