HARNESSING DEEP LEARNING FOR PROACTIVE THREAT DETECTION IN CYBERSECURITY FRAMEWORKS

Johan, Svensson and Meera, Chandrasekar (2024) HARNESSING DEEP LEARNING FOR PROACTIVE THREAT DETECTION IN CYBERSECURITY FRAMEWORKS. Journal of Adaptive Learning Technologies, 1 (8). pp. 20-36. ISSN 2997-3902

Text HARNESSING DEEP LEARNING FOR PROACTIVE.pdf Download (593kB)

Abstract

As cyber threats continue to evolve in complexity and scale, traditional security methods struggle to keep pace with the rapidly changing landscape. Deep learning, a subset of artificial intelligence, offers a transformative approach to proactive threat detection within cybersecurity frameworks. This paper explores the potential of deep learning algorithms to enhance threat detection capabilities by identifying patterns, anomalies, and potential vulnerabilities in real time. We examine how neural networks, particularly convolutional and recurrent networks, can be trained to detect novel and sophisticated attack vectors, from zero-day exploits to advanced persistent threats. The study highlights the advantages of deep learning in automating threat identification, reducing false positives, and providing adaptive defenses that learn from each attack. Furthermore, we discuss the integration of deep learning into existing cybersecurity infrastructures, addressing challenges such as computational demands, data privacy, and model interpretability. Our findings underscore the ability of deep learning to offer a proactive, adaptive, and scalable solution for modern cybersecurity frameworks, enhancing their ability to detect, respond to, and mitigate threats before they cause significant harm.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	19 Mar 2025 09:10
Last Modified:	19 Mar 2025 09:10
URI:	http://eprints.umsida.ac.id/id/eprint/15848

Actions (login required)

View Item