American
International
University-
Bangladesh

Students & Supervisors

Abstract

"Cyber-security incidents are an ever-growing threat to key sectors of industry. As such, it is important that we achieve a better understanding of the statistics relating to these incidents and the factors that affect the success or otherwise of attacks as well as the behavior of organizations in response to an attack. The sampled data from the study includes a secondary dataset, Cybersecurity Incident Dataset, obtained from the Kaggle data repository, comprising 600 incidents of cyberattack from September 2023 to September 2024. Eight types of attack were covered, namely Zero-Day Exploit, Malware, Ransomware, DDoS, among others. Different types of sectors were in the study including Energy, Finance, Healthcare, and Government. Main aim is to identify the statistical relation between attack severity, attack period, data compromised, and incident response time. The second aim is to develop a regression model to account for incident response time as a function of incident variables. The authors applied Pearson correlation to the four continuous variables for the bivariate relationships which were followed by multiple linear regression. The authors took response time and attack severity; The data compromised in gigabytes and period of attack as dependent variable. The correlation results indicated that all variable pairs were weakly associated with each other as indicated by coefficients that were almost zero. This suggests that response time is not really dependent on one attack feature. The R-squared of the regression model was 0.0027, indicating that all the predictors explained less than 1% of the variation in response time. The coefficient for attack severity was -0.107, while data compromised was -0.013. Based on the regression model, incident response time depends on qualitative factors other than attack type and volume. Organizational preparedness and industry protocols, for instance, Security tools efficiency, also influence their use. It is interesting to note that over half (53%). These datasets had successful attacks. This study found that the regression and correlation provide a good statistical starting point for informing. Examination of Cyber Incidents. Future studies should also include additional behavioral and organizational aspects. Factors that enhance fit. Organizations should focus on minimizing the time taken to respond. by a focused approach to threat syndicates – through their automated detection and sharing of cross-sector threat intelligence, rather than being severity-focused. The sole mechanism for response."

Keywords

Publication Details

• Type of Publication:
• Conference Name: " International Conference on Emerging Frontiers in Advanced Sciences and Technologies 2026"
• Date of Conference: 27/06/2026 - 27/06/2026
• Venue: Pabna University of Science and Technology (PUST)
• Organizer: Pabna University of Science and Technology (PUST) and Universiti Malaysia Perlis (UniMAP)