ANN-Based Intelligent Secure Routing Protocol in Vehicular Ad Hoc Networks (VANETs) Using Enhanced AODV.

Area of Science:

• Computer Science
• Network Security
• Wireless Communication

Background:

• Vehicular ad hoc networks (VANETs) are crucial for vehicle-to-vehicle and vehicle-to-infrastructure communication, relying on 5G technology.
• Black hole attacks pose a significant threat to VANET security by disrupting data packet forwarding.
• Existing routing protocols struggle to effectively mitigate these security challenges, especially in high-speed scenarios.

Purpose of the Study:

• To develop an intelligent cluster-based routing protocol for VANETs to enhance security and efficiency.
• To mitigate the impact of black hole attacks in VANETs.
• To improve data packet transmission reliability and minimize delays.

Main Methods:

• An artificial neural network (ANN) model was employed for malicious node detection.
• Enhanced clustering algorithms established clusters with designated cluster heads (CH).
• A modified Ad hoc On-Demand Distance Vector (AODV) protocol was integrated for optimal path selection, improving RREQ and RREP protocols.

Main Results:

• The ANN classifier achieved 98.97% accuracy in detecting black hole attacks.
• The proposed protocol demonstrated superior performance in network routing parameters compared to existing methods.
• Simulations using NS-2.33 showed reduced end-to-end delay, improved throughput, and lower hop count.

Conclusions:

• The intelligent cluster-based routing protocol effectively detects and mitigates black hole attacks in VANETs.
• The integration of ANN and modified AODV enhances network security and routing efficiency.
• This approach offers a promising solution for secure and reliable communication in dynamic vehicular environments.