The cybersecurity community is slowly leveraging machine learning (ML) to
combat ever-evolving threats. One of the biggest drivers for the successful
adoption of these models is how well domain experts and users can under­
stand and trust their functionality. Most models are perceived as a black box
despite the growing popularity of machine learning models in cybersecurity
applications (e.g., an intrusion detection system (IDS)). As these black-
box models are employed to make meaningful predictions, the stakeholders’
demand for transparency and explainability increases. Explanations support­
ing the output of ML models are crucial in cybersecurity, where experts
require far more information from the model than a simple binary output for
their analysis.