Analysing Cyber Threats: A Comprehensive Literature Review on Data-Driven Approaches

Abstract

This literature review paper aims to examine and analyze the existing research on prediction models for different types of cyber-attacks. Four key research papers have been selected as the base for this review: "A Prediction Model of DoS Attack's Distribution Discrete Probability," "Apriori Viterbi Model for Prior Detection of Socio-Technical Attacks," "Cyber Attacks Prediction Model Based on Bayesian Network," and "Applying Data Science to Cybersecurity Network Attacks & Events.” An overview of the value of prediction models in cybersecurity and their function in reducing potential threats come first in the review. The methodology section outlines the search strategy used to identify relevant literature and the selection criteria for the base papers. The subsequent sections provide an overview of the field, highlighting the historical development and key theories or frameworks related to cyber-attack prediction. The themes or subtopics identified in the literature are discussed, focusing on the discrete probability distribution model of DoS attacks, the Apriori Viterbi model for detecting socio-technical attacks, the Bayesian network-based prediction model, and the application of data science in analyzing network attacks and events. The review critically evaluates the selected papers, analyzing their methodologies, findings, and limitations. It identifies gaps, controversies, and conflicting findings in the literature, paving the way for further research in the field. The synthesis and interpretation section integrates the findings from the different studies, compares various perspectives, and discusses the implications and significance of the literature for cyber-attack prediction. In conclusion, this literature review paper provides a comprehensive analysis of prediction models for cyber-attacks, based on the selected base papers. It highlights the strengths and weaknesses of existing approaches, identifies research gaps, and offers recommendations for future studies. This review contributes to the advancement of knowledge in the field of cybersecurity and aids in the development of more effective prediction models to combat evolving cyber threats.