Home / Current Issue / Paper 1710384
Integrating Machine Learning with Zero Trust Principles for Real-Time Threat Detection and Response
Subject area: Science,Engineering and Technology · Area of research: Zero Trust Security
Abstract
The rapid advancement of cyber threats has rendered traditional perimeter-based security approaches insufficient, necessitating the development of adaptive and intelligent solutions. Zero Trust Architecture (ZTA), grounded in the principles of "never trust, always verify?, represents a paradigm shift that enforces continuous authentication, authorization, and least-privilege access across digital ecosystems (Stafford, 2020; Syed et al., 2022). Although ZTA enhances the security posture, its static policy enforcement mechanisms often face challenges in addressing real-time, high volume cyberattacks. Machine learning (ML), with its capabilities in anomaly detection, behavioral analysis, and predictive modelling, offers a dynamic layer that can augment ZTA for proactive and real-time threat detection (Gudula et al., 2021; Okoli et al., 2024). This study investigates the integration of ML techniques into Zero Trust principles to design a hybrid framework capable of continuous verification, adaptive response, and real-time anomaly mitigation. Utilizing benchmark cybersecurity datasets and advanced ML algorithms, the proposed framework demonstrates improvements in detection accuracy, scalability, and automated response latency over conventional models. These findings underscore the synergistic potential of combining ML with ZTA, establishing a pathway for next-generation cybersecurity frameworks applicable across cloud, IoT, and enterprise infrastructures (Paul et al., 2024; Tiwari et al., 2022). This study contributes to the advancement of secure digital ecosystems by proposing a holistic model that addresses both the strengths and limitations of current ML-augmented Zero Trust systems.
Keywords
Zero Trust Architecture, Machine Learning, Cybersecurity, Real-Time Threat Detection, Adaptive Security, Intrusion Detection, Automated Response
How to cite this paper
@article{1710384,
author = {Mukul Mangla},
title = {Integrating Machine Learning with Zero Trust Principles for Real-Time Threat Detection and Response},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {7},
number = {9},
pages = {564-575},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1710384.pdf},
abstract = {The rapid advancement of cyber threats has rendered traditional perimeter-based security approaches insufficient, necessitating the development of adaptive and intelligent solutions. Zero Trust Architecture (ZTA), grounded in the principles of "never trust, always verify?, represents a paradigm shift that enforces continuous authentication, authorization, and least-privilege access across digital ecosystems (Stafford, 2020; Syed et al., 2022). Although ZTA enhances the security posture, its static policy enforcement mechanisms often face challenges in addressing real-time, high volume cyberattacks. Machine learning (ML), with its capabilities in anomaly detection, behavioral analysis, and predictive modelling, offers a dynamic layer that can augment ZTA for proactive and real-time threat detection (Gudula et al., 2021; Okoli et al., 2024). This study investigates the integration of ML techniques into Zero Trust principles to design a hybrid framework capable of continuous verification, adaptive response, and real-time anomaly mitigation. Utilizing benchmark cybersecurity datasets and advanced ML algorithms, the proposed framework demonstrates improvements in detection accuracy, scalability, and automated response latency over conventional models. These findings underscore the synergistic potential of combining ML with ZTA, establishing a pathway for next-generation cybersecurity frameworks applicable across cloud, IoT, and enterprise infrastructures (Paul et al., 2024; Tiwari et al., 2022). This study contributes to the advancement of secure digital ecosystems by proposing a holistic model that addresses both the strengths and limitations of current ML-augmented Zero Trust systems.},
keywords = {Zero Trust Architecture, Machine Learning, Cybersecurity, Real-Time Threat Detection, Adaptive Security, Intrusion Detection, Automated Response},
month = {March},
}