1 Computer Science, College of Engineering, University of New Haven, USA.
2 Cybersecurity and Networks, College of Engineering, University of New Haven, USA.
International Journal of Science and Research Archive, 2025, 15(02), 063-080
Article DOI: 10.30574/ijsra.2025.15.2.1292
Received on 23 March 2025; revised on 30 April 2025; accepted on 02 May 2025
The growing proliferation of connected devices and distributed networks has amplified the complexity and vulnerability of modern cyber ecosystems. Traditional centralized security architectures, often reactive and bandwidth-dependent, are increasingly inadequate to manage the velocity and sophistication of cyber threats targeting critical systems. In this evolving landscape, the integration of edge computing, data science, and advanced cyber defense methodologies emerges as a pivotal strategy for achieving autonomous, real-time threat mitigation. Edge computing decentralizes data processing, bringing computational power closer to the source of data generation, thereby reducing latency and enabling localized, context-aware security interventions. This paper examines the synergistic application of edge analytics, machine learning models, and adaptive cybersecurity frameworks to create resilient, autonomous defense architectures. It explores how real-time anomaly detection, behavioral profiling, and predictive analytics, deployed at the network edge, can proactively identify, contain, and neutralize cyber threats before they propagate across broader infrastructures. The study also discusses advanced techniques such as federated learning, zero-trust architectures, and AI-driven threat hunting as enablers of scalable, decentralized cyber resilience. Drawing on case studies from critical sectors including healthcare, industrial control systems, and smart city infrastructures, the paper demonstrates how integrated edge and data science approaches significantly reduce response times, bandwidth burdens, and exposure to emerging threats. Finally, it critically evaluates the challenges of implementing autonomous cyber defense systems, including issues of model drift, adversarial attacks, and ethical governance. The findings affirm that the convergence of edge computing and intelligent cybersecurity is foundational to the next generation of proactive, self-healing cyber defense ecosystems.
Edge Computing Security; Autonomous Threat Mitigation; Cyber Defense Architecture; Machine Learning for Cybersecurity; Real-Time Anomaly Detection; Federated Learning in Security
Preview Article PDF
Rhoda Ajayi and Martha Masunda. Integrating edge computing, data science and advanced cyber defense for autonomous threat mitigation. International Journal of Science and Research Archive, 2025, 15(02), 063-080. Article DOI: https://doi.org/10.30574/ijsra.2025.15.2.1292.
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0







