Editor/Reviewer login
Frequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
Home Archives Volume 13 Issue 9 ijcatr13091005

IJCATR Volume 13 Issue 9

Leveraging Machine Learning for Proactive Threat Analysis in Cybersecurity

Moshood Yussuf, Adedeji O. Lamina, Olubusayo Mesioye, Gerald Nwachukwu, Teslim Aminu
10.7753/IJCATR1309.1005
keywords : Proactive Threat Analysis; Cybersecurity; Machine Learning; Threat Detection; Anomaly Detection

PDF
In the evolving cybersecurity landscape, traditional reactive methods are increasingly inadequate. This article explores the transformative potential of machine learning (ML) in proactive threat analysis, aiming to pre-emptively identify and neutralize threats before they emerge. By employing ML algorithms, cybersecurity systems can analyse vast datasets in real time, recognize patterns, and detect anomalies indicating potential threats. The article reviews current cybersecurity challenges, examines how ML techniques—such as decision trees, neural networks, and clustering—are utilized in threat analysis, and assesses various ML-driven cybersecurity solutions through literature, case studies, and analysis. It highlights ML's benefits, including enhanced detection accuracy, quicker responses, and future threat prediction capabilities. However, challenges such as data quality, adversarial attacks, and high computational demands are also discussed. The article concludes by addressing these limitations and suggesting that while ML offers a promising approach, its success depends on overcoming these hurdles. Emerging trends and future directions emphasize the need for continued research and development in ML for cybersecurity.
@artical{m1392024ijcatr13091005,
Title = "Leveraging Machine Learning for Proactive Threat Analysis in Cybersecurity",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "13",
Issue ="9",
Pages ="53 - 64",
Year = "2024",
Authors ="Moshood Yussuf, Adedeji O. Lamina, Olubusayo Mesioye, Gerald Nwachukwu, Teslim Aminu"}
  • The paper demonstrates the proactive potential of machine learning in pre-emptively identifying cyber threats.
  • Various ML techniques, such as decision trees and neural networks, are evaluated for their effectiveness in threat analysis.
  • The study highlights the advantages of ML-driven cybersecurity, including enhanced detection accuracy and quicker response times.
  • Challenges such as data quality and adversarial attacks are discussed, with suggestions for overcoming these hurdles.
Copyright © 2012-2024 International Journal of Computer Applications Technology and Research All Rights Reserved.