Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.076825
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

A Unified API-Driven IPAM Framework with LSTM-Based Anomaly Detection for Hybrid Cloud Environments

Mohammed Saad Javeed1, MD AL Rafi2, Arifa Akter Eva3, Muhammad Firoz Mridha3, Qiangfu Zhao4,*, Jungpil Shin4,*
1 Information Science, Trine University, Angola, IN, USA
2 Information Technology, Washington University of Science and Technology, 2900 Eisenhower Ave, Alexandria, VA, USA
3 Department of Computer Science and Engineering, American International University-Bangladesh (AIUB), Dhaka, Bangladesh
4 School of Computer Science and Engineering, The University of Aizu, Aizu-wakamatsu, Japan
* Corresponding Author: Qiangfu Zhao. Email: email; Jungpil Shin. Email: email
(This article belongs to the Special Issue: Advances in Machine Learning and Artificial Intelligence for Intrusion Detection Systems)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.076825

Received 27 November 2025; Accepted 05 March 2026; Published online 06 May 2026

Abstract

Hybrid and multi-cloud infrastructures make IP address management (IPAM) difficult, especially when IP and Domain Name System (DNS) records must stay consistent across on-premises networks and cloud platforms. Traditional IPAM tools often lack deep automation and cross-platform visibility, which leads to DNS drift, IP conflicts, and configuration errors. This paper proposes a unified, Application Programming Interface (API)-driven IPAM framework that integrates Infoblox Network Identity Operating System (NIOS) with Amazon Web Services (AWS) Route53 and Azure DNS using Infrastructure-as-Code and CI/CD pipelines. We generate an IPAM event log from Infoblox API simulations and fuse it with the UNSW-NB15 cybersecurity dataset to train a deep Long Short-Term Memory (LSTM)-based anomaly detection model. On this fused dataset, the propose model achieves an accuracy of 0.912 and an F1-score of 0.900, outperforming Random Forest, Logistic Regression, one-dimensional convolutional neural network (1D-CNN), and Gated Recurrent Unit (GRU) baselines. The automation pipeline also reduces end-to-end provisioning latency to 1010 ms and improves DNS consistency to 99.1% across Infoblox, AWS, and Azure. The framework provides scalable, auditable, and policy-driven IPAM while reducing manual work and configuration drift in hybrid cloud environments.

Keywords

IP address management (IPAM); API automation; anomaly detection; hybrid cloud; DNS synchronization; network automation

  • 201

    View

  • 77

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link