DDoS Attack Detection using Machine Learning

  • Unique Paper ID: 163731
  • Volume: 10
  • Issue: 11
  • PageNo: 2003-2008
  • Abstract:
  • Distributed Denial of Service (DDoS) attacks continue to pose significant threats to the availability and integrity of online services. Addressing this challenge necessitates the development of robust and efficient detection systems capable of swiftly identifying and mitigating malicious traffic. In this paper, we propose a hybrid DDoS detection system leveraging a combination of machine learning algorithms, including Random Forest, Logistic Regression, Decision Tree, and Support Vector Machine (SVM). The system operates in real-time, continuously monitoring incoming network traffic for anomalous patterns indicative of DDoS attacks. Leveraging the versatility of Random Forest, Logistic Regression, Decision Tree, and SVM algorithms, the system constructs a comprehensive feature space encompassing various network traffic attributes such as packet size, packet frequency, source IP reputation, and traffic volume. The proposed system employs Random Forest to handle complex and nonlinear relationships within the feature space, Logistic Regression for probabilistic modeling and binary classification, Decision Tree for hierarchical partitioning of data, and SVM for effective separation of normal and anomalous traffic patterns in high-dimensional spaces. By integrating these diverse algorithms, the system achieves enhanced accuracy, scalability, and resilience against sophisticated DDoS attacks.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 10
  • Issue: 11
  • PageNo: 2003-2008

DDoS Attack Detection using Machine Learning

Related Articles