Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?
This work provides a scalable measure of instructional alignment for cybersecurity training exercises, offering both predictive and diagnostic insights, though it is incremental in applying existing multimodal methods to this domain.
The researchers tackled the problem of measuring instructional alignment in cybersecurity simulations by analyzing multimodal data from 23 teams, finding that alignment (discrepancy between required and enacted cognitive levels) predicts success, and that combining text embeddings and log features best forecasts performance with a test AUC of 0.80.
Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23 teams (76 students) across five exercise sessions. Study 1 codes objectives and team emails with Bloom's taxonomy and models the completion of key exercise tasks with generalized linear mixed models. Alignment, defined as the discrepancy between required and enacted Bloom levels, predicts success, whereas the Bloom category alone does not predict success once discrepancy is considered. Study 2 compares predictive feature families using grouped cross-validation and l1-regularized logistic regression. Text embeddings and log features outperform Bloom-only models (AUC~0.74 and 0.71 vs. 0.55), and their combination performs best (Test AUC~0.80), with Bloom frequencies adding little. Overall, the work offers a measure of alignment for simulations and shows that multimodal traces best forecast performance, while alignment provides interpretable diagnostic insight.