Automated Vulnerability Assessment Using Machine Learning

EasyChair Preprint 14347

Abstract

In the rapidly evolving landscape of cybersecurity, traditional vulnerability assessment methods struggle to keep pace with the increasing complexity and volume of potential threats. This paper explores the integration of machine learning techniques to enhance automated vulnerability assessment. By leveraging advanced algorithms, such as supervised learning, unsupervised learning, and reinforcement learning, we develop a system capable of identifying, categorizing, and prioritizing vulnerabilities with greater accuracy and efficiency than conventional methods. Our approach involves training machine learning models on historical vulnerability data to predict new and emerging threats, thus enabling proactive security measures. We evaluate the effectiveness of our system through empirical analysis and case studies, demonstrating significant improvements in detection rates and reduced false positives. The results indicate that machine learning can substantially augment automated vulnerability assessment processes, offering a promising solution to the challenges posed by modern cyber threats.

Keyphrases: Cyber Security, learning, machine

@booklet{EasyChair:14347,
  author    = {Obaloluwa Ogundairo and Peter Broklyn},
  title     = {Automated Vulnerability Assessment Using Machine Learning},
  howpublished = {EasyChair Preprint 14347},
  year      = {EasyChair, 2024}}