Enhancing IT Data Protection: A Multi-Layered Approach with Contextual Access and Automated Incident Response
Year: 2025
Type: article
Abstract: This paper presents an innovative, multi-layered cybersecurity framework for the utility industry, integrating a suite of advanced AI and ML techniques to enhance data security. At its core, the solution employs a machine learning based adaptive risk scoring engine that aggregates diverse data inputs such as endpoint metrics, geolocation, device integrity, and historical user behaviour to deliver real-time, contextual risk assessments. These insights drive dynamic contextual access management, which dynamically adjusts user privileges, and an automated incident response platform that classifies threats and initiates predefined countermeasures, thereby reducing response times and mitigating breach impacts. The framework is further augmented by explainable AI for transparent decision-making, federated learning for secure, collaborative threat detection, AI-driven vulnerability management and patch prioritization, cyberattack simulation using generative models, edge AI for ultra-low latency threat detection, and comprehensive cyber risk quantification for informed strategic resource allocation. Collectively, these methods create a resilient, adaptive security posture that not only mitigates risks but also empowers organizations to proactively manage evolving cyber threats in an increasingly complex digital landscape.
Authors: Prakash Lande, Shubham Sawant, Hardik Gunde
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6949207846
FWCI:
Cites:
Cited by:
Related to: