PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
August 26, 2026Journal of Computer Virology and Hacking TechniquesOpen Access

Reliability auditing of explanations for machine-learning-based intrusion detection systems

View Full Paper
Ask AI
Bookmark
Share

Authors

EMElijah M. MasenoYSYanxia SunZWZenghui Wang

Discussion

Loading...

Member takes

Overview

Comparative evaluation demonstrates explanation discrepancies despite high detection performance across cybersecurity datasets, highlighting the need for explanation-reliability audits.

Key Points

  • To develop and evaluate a comprehensive quantitative framework for auditing the reliability and stability of Explainable Artificial Intelligence (XAI) methods in machine-learning-based intrusion detection systems.
  • Assessed XGBoost, Random Forest, and Logistic Regression models on untouched test sets of the UNSW-NB15 and IoT-ToN network security benchmark datasets.
  • Audited explanation reliability using SHAP attributions, permutation importance ranking agreement, retraining stability, sufficiency and comprehensiveness retraining tests, and spurious-feature injection.
  • On UNSW-NB15, Random Forest and XGBoost achieved ROC AUCs of 0.9862 and 0.9858 (PR AUC: 0.9934 vs 0.9932; F1: 0.9231 vs 0.9217), outperforming Logistic Regression (ROC AUC: 0.9695, PR AUC: 0.9774, F1: 0.9037).
  • On IoT-ToN, XGBoost and Random Forest attained ROC AUC values of 0.9994 (F1: 0.9867 and 0.9879), while Logistic Regression degraded to an ROC AUC of 0.8502 (F1: 0.6081).
  • High predictive accuracy did not guarantee explanation reliability; Logistic Regression yielded the most stable explanations despite poor detection, whereas XGBoost and Random Forest provided the optimal explanation-accuracy balance across benchmarks.

Cite This Study

Maseno et al. (2026) studied this question.

synapsesocial.com/papers/6a8e9b58451774b83f3b40adhttps://doi.org/10.1007/s11416-026-00664-7
View Full Paper
Ask AI
Bookmark
Share