Ensemble Majority Voting-Based Hybrid Machine Learning Framework for Intrusion Detection in Secure Digital Banking Networks

Anil Kumar; Narender Kumar

Ensemble Majority Voting-Based Hybrid Machine Learning Framework for Intrusion Detection in Secure Digital Banking Networks

Author(s)	Mr. Anil Kumar, Prof. Narender Kumar
Country	India
Abstract	he growing dependence of digital banking services on always-on networked infrastructure has made intrusion detection, alert integrity, and post-detection auditability equally important design requirements. The experimental framework supplied with this study implements a practical intrusion-detection pipeline using multiple classical machine learning classifiers, an autoencoder, majority-voting ensembles, AES-based alert encryption, ECC-based signatures, and blockchain-inspired hash chaining. This paper simultaneously incorporates the most important technical corrections needed to elevate the work toward thesis and journal quality. The proposed framework adopts a corrected data-preparation pipeline that avoids scaling leakage, recommends stratified partitioning, preserves complete attack-category mappings, integrates the autoencoder explicitly into the hybrid decision layer, and extends the evaluation plan from a single-dataset experiment to a multi-dataset benchmark using NSL-KDD, CICIDS2017, and UNSW-NB15. Empirical results extracted from the experimental framework on NSL-KDD show that the best tested ensemble (NB+DT+RF) achieved 99.00% accuracy, 99.28% detection rate, and 1.23% false-alarm rate, while the secure alert pipeline produced low logging and cryptographic overhead. Beyond the raw detection phase, the work contributes a tamper-evident alert-governance mechanism in which attack alerts are encrypted using AES-EAX, signed with ECC, and appended to a hash-chained ledger. The methodologically honest, only the NSL-KDD performance values are treated here as experimental framework-validated empirical results; the paper includes a full, submission-ready protocol for extending the same framework to CICIDS2017 and UNSW-NB15 without overstating unexecuted cross-dataset claims.
Keywords	Intrusion detection system, ensemble majority voting, autoencoder, AES-EAX, ECC digital signature, NSL-KDD, CICIDS2017, UNSW-NB15
Field	Computer > Network / Security
Published In	Volume 17, Issue 1, January-March 2026
Published On	2026-03-30

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 17 Isu 1 Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2

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

Ensemble Majority Voting-Based Hybrid Machine Learning Framework for Intrusion Detection in Secure Digital Banking Networks

Share this