Abstract :

Cyberattacks On Modern Networks Are Increasing In Volume, Speed, And Sophistication, Making Timely Detection And Prediction Essential For Maintaining Network Security. Conventional Intrusion Detection Approaches Often Rely On Static Signatures And Manual Analysis, Limiting Their Ability To Identify Novel Or Rapidly Evolving Threats. Recent Advances In Data-driven Machine Learning Provide Opportunities For Predictive Intrusion Detection, Anomaly Identification, And Automated Network Defense [1], [2]. This Paper Presents An Intelligent Cyberattack Prediction Framework That Applies Data-driven Machine Learning Models To Enhance Network Security. Existing Approaches, Including Classical Machine Learning, Deep Learning, And Hybrid Models, Are Reviewed With Respect To Their Detection Accuracy, Scalability, And Limitations [6]–[11], [13]. Based On This Survey, A Data-driven Prediction Framework Is Proposed That Integrates Data Preprocessing, Feature Selection, Model Training, And Real-time Attack Classification. The Paper Further Discusses Evaluation Metrics, Benchmark Datasets, And Research Challenges Toward Building Reliable, Adaptive, And Scalable Cyberattack Prediction Systems For Real-world Network Environments [14], [16].

Published:

21-9-2026

Issue:

Vol. 26 No. 9 (2026)

Page Nos:

285 - 290

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite