Enhanced Stacked Ensemble Learning for Cloud-Based Darknet Traffic Analysis and Classification
D Vijay, Vigneshwaran V, Titus Casimir. A, Avinash B, Dontabhaktuni Jayakumar · 2024
To improve cybersecurity threat identification and incident response capabilities, the suggested cloud-based darknet traffic analysis and categorization system incorporates cutting-edge machine learning algorithms and data pretreatment techniques. The system uses altered stacking ensemble learning techniques to combine several threat intelligence sources to improve its comprehension of new cyber threats that are present in the darknet environment. Cloud infrastructure-enabled real-time incident response techniques allow for quick threat containment and mitigation. Predictive models for cybersecurity threat detection are more accurate and dependable by employing adaptive data preparation techniques. By facilitating stakeholder exchange of real-time threat intelligence, the system, which emphasizes collaborative frameworks, encourages proactive cybersecurity actions. Adherence to data privacy laws and industry best practices is ensured by seamless integration with regulatory compliance requirements. By using the suggested method, threat detection efficiency and accuracy have significantly improved, enabling enterprises to successfully foresee and counteract cyberthreats originating from the darknet.