Firewall Defense and Response Policy towards Resisting Attacks on Network Logs

  • Onate E. Taylor Department of Computer Science, Rivers State University, Nigeria
  • Promise S. Ezekiel Department of Computer Science, Rivers State University, Nigeria

Abstract

Background – In an era marked by escalating cyber threats, safeguarding network infrastructure and preserving the integrity of network logs have become paramount concerns for organizations worldwide

Objective: This paper proposes a robust Firewall Defense and Response Policy leveraging a state-of-the-art Gradient Boost Classifier to achieve exceptional accuracy in detecting cyber threats.

Methods – The proposed methodology combines advanced machine learning techniques with an in-depth analysis of network logs. The model was trained on a comprehensive dataset, downloaded from Kaggle.com, comprising 65,533 instances of diverse attack vectors. This training enables the model to discern subtle patterns indicative of cyber threats.

Results – The Gradient Boost Classifier achieved an accuracy of 99.99% in identifying and thwarting malicious intrusion attempts. The Response Policy integrates an adaptive approach, dynamically adjusting countermeasures based on the severity and nature of detected anomalies.

Conclusion – Through extensive experimentation and validation, the proposed approach demonstrates superior performance in detecting and mitigating a wide spectrum of attacks, including sophisticated and evasive tactics. This paper contributes a highly effective and resilient framework for bolstering network security, empowering organizations to fortify their defenses against evolving cyber threats and safeguard the integrity of their network logs.

Recommendation – Organizations should implement the proposed Firewall Defense and Response Policy across various environments, regularly update the training dataset with new attack vectors, and periodically re-evaluate the model to maintain its effectiveness. Integrating this policy with existing security systems, training personnel, and promoting awareness about cyber threats will optimize its implementation. Continued research into advanced machine learning techniques will further enhance the system's accuracy and resilience.

Author Biographies

Onate E. Taylor, Department of Computer Science, Rivers State University, Nigeria

Onate E. Taylor obtained his B.Sc, M.Sc, and Ph.D degrees all in Computer Science from the Rivers State University of Science and Technology, University of Ibadan, and University of Port Harcourt, Nigeria respectively. He is currently an Associate Professor in the Department of Computer Science, Rivers State University, Port Harcourt, Nigeria. He is a chartered member of the Computer Professionals (Registration Council) of Nigeria and Nigeria Computer Society. His research focuses on machine intelligent systems, context-aware systems, and pervasive systems. He has over sixty academic publications and more than fifteen years of teaching and research experience.

Promise S. Ezekiel, Department of Computer Science, Rivers State University, Nigeria

Promise S. Ezekiel is an AI developer with a BSc and MSc in Computer Science from Rivers State University, I have over twenty publications online, showcasing my expertise in machine learning, deep learning, and computer vision. Specializing in cybersecurity, smart systems, and blockchain technology, my research aims to advance the fields through innovative solutions that enhance security, efficiency, and transparency. My passion lies in pushing the boundaries of technology to create a smarter, more secure, and sustainable future for all.

Published
2024-06-02
How to Cite
TAYLOR, Onate E.; EZEKIEL, Promise S.. Firewall Defense and Response Policy towards Resisting Attacks on Network Logs. International Journal of Computing Sciences Research, [S.l.], v. 8, p. 2886-2904, june 2024. ISSN 2546-115X. Available at: <//stepacademic.net/ijcsr/article/view/459>. Date accessed: 09 oct. 2024.
Section
Articles