Skip to content
Open access

Toward Transparent Intrusion Detection Systems: An Explainable Ai Approach For Network Security

Jul 2026 · Journal of Information Technology, Cybersecurity, and Artificial Intelligence · Vol 3, pp. 135-148 · 0 citations · 14 references

TL;DR

This paper treated the proposed IDS as a two-class problem identifying both normal and attack flows and evaluated it using a variety of comprehensive performance metrics such as accuracy, precision, recall, F1 score, confusion matrices, and Receiver Operating Characteristic Area Under Curve (ROC-AUC).

Abstract

The growth in use of machine-learning based intrusion detection systems (IDS), however, also raises critical issues of transparency, trust, and accountability due to the fact that most of the top performing models are "black box" models. Lack of ability to provide explanation of detection decisions severely limits the operability of IDSs in critical security areas and reduces the confidence analysts have in their decision making processes. Therefore, the objective of this research was to determine if excellent intrusion detection performance could be obtained without loss of interpretability. For that purpose, this paper proposes an inherent explanatory IDS framework. The method used logistic regression as a classification model and evaluated its performance on the entire UNSW-NB15 dataset using flow-based statistics as input to logistic regression. This paper treated the proposed IDS as a two-class problem identifying both normal and attack flows and evaluated it using a variety of comprehensive performance metrics such as accuracy, precision, recall, F1 score, confusion matrices, and Receiver Operating Characteristic Area Under Curve (ROC-AUC). The experimental results demonstrated that the explanatory model had an average accuracy of 87.5%, an AUC value of .9697, and therefore good discriminant ability. Further, the experiments provided evidence that the model's good performance did not depend significantly on the balance between classes, but instead had high precision for attacks and performed consistently over several views. 

Read PDF

Similar papers

Open access Sep 2026

ENHANCING INTRUSION DETECTION SYSTEMS WITH AI-BASED NETWORK TRAFFIC ANALYSIS: A FOCUS ON ANOMALY DETECTION

An intelligent approach based on event log analysis and machine learning methods is proposed to identify signs of potential information leaks in intrusion detection systems and demonstrates the advantages of regularized linear models.

G. Ziyatbekova, G. Kydyrbayeva, Gulmira Rahimzhanova et al. · 0 citations
Open access Oct 2026

A Comparative Study on the Performance of Explainable Artificial Intelligence-Based Intrusion Detection Systems

In the modern cybersecurity landscape, the increasing sophistication and diversity of network attacks have significantly reduced the effectiveness of traditional Intrusion Detection Systems (IDS). At the same time, Artificial Intelligence (AI)-based IDS models often operate as black boxes, limiting transparency and hin...

Enkhbayar Batjargal, Usukhbayar Baldangombo, Ugtakhbayar Naidansuren · 0 citations
Conference Open access 2026

Comparative Evaluation of Explainable AI-Driven Intrusion Detection Systems: Performance, Interpretability, and Scalability Analysis

Rapid advancements in cybersecurity have made it necessary for developing intelligent, as well as transparent, intrusion detection systems. Explainable Artificial Intelligence (XAI) has become an important concept in providing greater interpretability and accountability in machine learning-based IDSs. This paper conduc...

Nita Dimble, S. Gujar · 0 citations
Open access Oct 2026

ADAPTIVE DECISION-MAKING MODEL FOR HYBRID INTRUSION DETECTION SYSTEMS

The increasing complexity of cyber threats, together with the limitations of traditional intrusion detection systems based exclusively on signature analysis or probabilistic machine learning models, creates a need for comprehensive adaptive decision-making models. Although machine learning methods can provide high sens...

A. Davletova · 0 citations
Review Open access Nov 2026

EARLY DETECTION OF NETWORK INTRUSIONS USING MACHINE LEARNING TECHNIQUES: A SYSTEMATIC LITERATURE REVIEW

The rising complexity and sophistication of threats in network traffic pose significant challenges that require precise and reliable Intrusion Detection Systems (IDSs). In recent years, these systems have gained considerable attention due to their continuously improving performance. The early detection of breaches is c...

Russell Jassim Alabedi, A. Alawadi · 0 citations
Open access Sep 2026

An Ensemble Machine Learning Based Cybersecurity IntrusionDetection System (C-IDS)

An essential component of network security is intrusion detection, which shields computer systems against attacks and illegal access. Traditional intrusion detection systems (IDS) rely on signature-based detection, which limits their ability to detect unknown complex threats. Machine learning-based methods have demonst...

A. Ilyas, Muhammad Faisal Laiq Siddiqui, Farheen Siddiqui et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.