An Adaptive DDoS Detection and Classification Method in Blockchain Using an Integrated Multi-Models

Abstract

With the rising adoption of blockchain technology due to its decentralized, secure, and transparent features, ensuring its resilience against network threats, especially Distributed Denial of Service (DDoS) attacks, is crucial. This research addresses the vulnerability of blockchain systems to DDoS assaults, which undermine their core decentralized characteristics, posing threats to their security and reliability. We have devised a novel adaptive integration technique for the detection and identification of varied DDoS attacks. To ensure the robustness and validity of our approach, a dataset amalgamating multiple DDoS attacks was derived from the CIC-DDoS2019 dataset. Using this, our methodology was applied to detect DDoS threats and further classify them into seven unique attack subcategories. To cope with the broad spectrum of DDoS attack variations, a holistic framework has been proposed that seamlessly integrates five machine learning models: Gate Recurrent Unit (GRU), Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM), Deep Neural Networks (DNN), and Support Vector Machine (SVM). The innovative aspect of our framework is the introduction of a dynamic weight adjustment mechanism, enhancing the system's adaptability. Experimental results substantiate the superiority of our ensemble method in comparison to singular models across various evaluation metrics. The framework displayed remarkable accuracy, with rates reaching 99.71% for detection and 87.62% for classification tasks. By developing a comprehensive and adaptive methodology, this study paves the way for strengthening the defense mechanisms of blockchain systems against DDoS attacks. The ensemble approach, combined with the dynamic weight adjustment, offers promise in ensuring blockchain's enduring security and trustworthiness.