Spiking Neural Network Model for Detection Spoofing Attacks in Vehicular Ad-Hoc Networks

The security and dependability of Vehicular Ad-hoc Networks (VANETs) are seriously threatened by spoofing attacks. Malicious entities have the ability to undermine the integrity of vehicular communication through the forgery or falsification of communications, which can result in serious repercussions including infrastructure damage, traffic accidents, and privacy violations. To identify spoofing attacks in VANETs effectively, a Spiking Neural Network (SNN) model is introduced in this research. Their event-driven design allows for more effective processing of network traffic data since it complements the dynamic and asynchronous character of vehicular communication. Because of their sparse coding scheme, SNNs may be able to achieve reduced energy consumption and greater computing efficiency. Furthermore, SNNs have the ability to automatically represent temporal relationships in data, which is essential for accurately capturing how spoofing attacks change over time. Multiple layers of spiking neurons in the SNN architecture allow for the extraction of complex information from unprocessed network traffic data. Extensive experiments were conducted using the Python language to evaluate the performance of the model. With a detection accuracy of 97.8% and a low false negative rate of 0.01, the proposed SNN model outperformed conventional machine learning and deep learning approaches in recognizing spoofing attacks, demonstrating its efficacy in identifying hostile nodes. This study offers a reliable and effective method for identifying spoofing attacks in VANETs, which makes a substantial contribution towards the progress of network security. The SNN model has the potential to raise the general level of safety and dependability of intelligent transportation systems and provides a viable method for handling difficult problems in vehicular communication systems.