AI in Real-Time Cybersecurity: Enhancing Threat Detection in Dynamic Networks

Authors: Ravi Kumar Perumallapalli

Country: USA

Full-text Research PDF File:   View   |   Download

Abstract: The proliferation of dynamic networks and the exponential growth of the Internet of Things (IoT) necessitate real-time, adaptive security solutions. Traditional static security models are inadequate for detecting and mitigating evolving cyber threats, particularly in resource-constrained environments. This paper explores the transformative potential of artificial intelligence (AI) in enhancing detection and response mechanisms within dynamic networks, emphasizing real-time cybersecurity applications. This paper proposes a hybrid approach that integrates supervised and unsupervised learning models for anomaly detection, alongside behavior-based automated incident responses and self-healing strategies. The deployment of AI in cybersecurity also addresses critical aspects such as data privacy, model explainability, and efficient resource utilization, especially within IoT ecosystems. Through empirical analysis and experimentation, this paper demonstrates that AI can optimize threat detection in dynamic networks, paving the way for high-performance, real-time cybersecurity solutions. The proposed architecture not only enhances scalability in intrusion detection systems but is also adaptable to emerging, complex cyber threats in today’s interconnected landscape.

Keywords: Artificial Intelligence, real-time cybersecurity, dynamic networks, machine learning, anomaly detection, neural networks, IoT security, automated incident response, self-healing strategies

Paper Id: 231510

Published On: 2019-01-03

Published In: Volume 7, Issue 1, January-February 2019

Cite This: AI in Real-Time Cybersecurity: Enhancing Threat Detection in Dynamic Networks - Ravi Kumar Perumallapalli - IJIRMPS Volume 7, Issue 1, January-February 2019.

Share this