DDoS attack detection in intelligent transport systems using adaptive neuro-fuzzy inference system

Area of Science:

• Computer Science
• Network Security
• Artificial Intelligence

Background:

• Intelligent Transportation Systems (ITS) are vital for traffic management and public benefit.
• ITS operate in dynamic environments, making them vulnerable to threats like Distributed Denial of Service (DDoS) attacks.
• Current DDoS detection methods in ITS have flaws, necessitating improved security solutions.

Purpose of the Study:

• To propose a robust Distributed Denial of Service attack detection scheme for Intelligent Transportation Systems.
• To enhance the security and reliability of the ITS ecosystem against cyber threats.
• To address the limitations of existing DDoS detection techniques in ITS.

Main Methods:

• Development of a Distributed Denial of Service attack detection scheme utilizing the Adaptive Neuro-Fuzzy Inference System (ANFIS).
• Integration of artificial neural network learning capabilities with fuzzy logic models within the ANFIS framework.
• Comparative analysis against traditional classifiers including Support Vector Machine, Random Forest, Extreme Gradient Boosting, and Convolutional Neural Network.

Main Results:

• The proposed ANFIS-based model achieved a high accuracy of 94.3% in detecting DDoS attacks.
• Demonstrated superior performance compared to Support Vector Machine, Random Forest, Extreme Gradient Boosting, and Convolutional Neural Network.
• Exhibited low false positive rates and high detection reliability, confirming its suitability for real-world ITS security.

Conclusions:

• The Adaptive Neuro-Fuzzy Inference System offers a highly effective solution for enhancing Intelligent Transportation Systems security.
• The proposed scheme provides significant improvements in accuracy, precision, recall, and F1 score for DDoS attack detection.
• The developed system is well-suited for real-world applications, ensuring the continuous and secure operation of ITS.