COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS FOR PREDICTING CYBERSECURITY ATTACK SUCCESS: A PERFORMANCE EVALUATION
Md Abu Sayed, Badruddowza Badruddowza, Md Shohail Uddin Sarker, Abdullah Al Mamun, Norun Nabi, Fuad Mahmud, Md Khorshed Alam, Md Tarek Hasan, Md Rashed Buiya, Mashaeikh Zaman Md. Eftakhar Choudhury · The American Journal of Engineering And Technology · 2024
This study explores the effectiveness of various machine learning algorithms in predicting the success of cybersecurity attacks by analyzing historical attack data. We evaluated five prominent algorithms—Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and K-Nearest Neighbors (KNN)—based on their performance metrics, including accuracy, precision, recall, F1-Score, and AUC-ROC. Our results indicate that Random Forest outperforms the other algorithms, achieving the highest accuracy (90%), precision (88%), recall (85%), F1-Score (86%), and AUC-ROC (0.92). Gradient Boosting also demonstrated strong performance with an accuracy of 88% and an AUC-ROC of 0.90, though it required more computational resources. Logistic Regression and SVM provided moderate results, while K-Nearest Neighbors showed the least effectiveness due to its lower performance metrics. The comparative analysis highlights Random Forest as the most effective model for predicting cybersecurity attack success, offering superior performance in handling complex data and distinguishing between attack outcomes. These findings provide valuable insights for improving cybersecurity strategies and selecting appropriate machine-learning models for threat prediction.