Explainable AI (XAI) for Enhanced Cyber Threat Intelligence: Building Interpretable Intrusion Detection Systems

Naresh Kalimuthu

doi:10.71097/IJSAT.v16.i4.9535

Explainable AI (XAI) for Enhanced Cyber Threat Intelligence: Building Interpretable Intrusion Detection Systems

Author(s)	Naresh Kalimuthu
Country	United States
Abstract	The growth of complex cyber threats calls for integrating advanced Artificial Intelligence (AI) and Machine Learning (ML) technologies into Cyber Threat Intelligence (CTI) frameworks, especially for Intrusion Detection Systems (IDS). While these models, particularly deep learning architectures, achieve high accuracy in identifying complex and unprecedented attacks, the "black-box" nature creates trust, adoption, and operational challenges. This lack of transparency often results in opaque decision-making, diminishes trust among security personnel, and increases alert fatigue, weakening the security these systems aim to provide. An emerging body of work in Explainable AI (XAI) addresses this issue by offering explanations for AI-driven decisions and actions. This paper examines the integration of XAI into IDS to enhance trust, collaboration, and resilience in cyber defense systems. It outlines three primary research challenges that have so far impeded the development of Explainable IDS (X-IDS): balancing model accuracy with system fidelity, meeting the technical requirements for real-time XAI processing, and establishing standards to evaluate explanation quality. This paper critically reviews various mitigation strategies, including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) post-hoc explainability frameworks, attention-based explainable AI models, and emerging federated and lightweight XAI paradigms. Syntheses of findings from CICIDS2017, UNSW-NB15, and other benchmark data that illustrate XAI’s potential to improve forensic analysis and reduce false positive rates without compromising detection accuracy. The paper argues that XAI is essential for the future of cyber threat intelligence (CTI), enabling IDS to evolve from opaque alert generators into trustworthy partners alongside human analysts. It calls for future research to develop federated, lightweight real-time XAI, unified benchmarking frameworks for XAI evaluation, and defenses against adversarial XAI sabotage.
Keywords	Explainable AI (XAI), Intrusion Detection System (IDS), Cyber Threat Intelligence (CTI), Machine Learning, Interpretability, SHAP, LIME, Network Security.
Field	Engineering
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-10-22
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9535
Short DOI	https://doi.org/hbb8gf

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Explainable AI (XAI) for Enhanced Cyber Threat Intelligence: Building Interpretable Intrusion Detection Systems

Share this