Machine learning based multi-stage intrusion detection system and feature selection ensemble security in cloud...

Area of Science:

• Computer Science
• Network Security
• Artificial Intelligence

Background:

• Vehicular Ad Hoc Networks (VANETs) are crucial for intelligent transportation systems but are vulnerable to security threats due to their dynamic and decentralized nature.
• Existing security measures in VANETs are insufficient to address the complexities of real-time threats, potentially compromising vehicle safety and efficiency.
• Advanced Intrusion Detection Systems (IDS) are required for real-time threat recognition and neutralization in VANETs.

Purpose of the Study:

• To propose a novel multi-stage Lightweight Intrusion Detection System Using Random Forest Algorithms (MLIDS-RFA) for enhanced VANET security.
• To improve the accuracy and efficiency of threat detection in VANETs through machine learning-based feature selection and ensemble models.
• To ensure the secure and reliable functioning of next-generation transportation networks.

Main Methods:

• Developed a multi-stage IDS (MLIDS-RFA) employing machine learning for feature selection to optimize processing overhead and response times.
• Integrated the Random Forest Algorithm (RFA) within ensemble models to enhance detection capabilities against complex network threats.
• Conducted thorough simulation analyses to evaluate the performance and practicality of the proposed MLIDS-RFA system.

Main Results:

• The MLIDS-RFA achieved a high detection accuracy of 96.2% and computing efficiency of 94.8% in dynamic VANET environments.
• Demonstrated excellent performance with large networks (97.8% detection) and adaptability to network changes (93.8%).
• The system effectively reduced false positives while maintaining high detection rates, achieving an overall detection performance of 95.9%.

Conclusions:

• The proposed MLIDS-RFA significantly enhances VANET security by balancing accuracy, efficiency, and scalability.
• This research provides a robust solution for real-time threat detection and neutralization in VANETs.
• The findings pave the way for future upgrades in VANET protection, ensuring the secure operation of intelligent transportation systems.