Authentication based vanet for data transfer: unveiling the ability of deep learning models for attack classification

Incorporating VANET in cloud computing plays a vital role in providing a reliable and a safer journey to the travelers on road. Whereas, attaining a secured process of message dissemination is a major bottleneck for a VANET in the cloud environment, due to their dynamic nature and huge wireless communication. The frequently used mechanism in the VANET are the systems for Intrusion Detection, which rely on vehicle collaboration for the identification of the attacks. The concepts of VANET presents and implements an intelligent solution for a traffic control in the modernized world. In context to these advantages of using VANET, many Artificial Intelligence (AI) based concepts such as Machine Learning (ML) models are established. Though, the outcomes from these models are not satisfactory in terms of their accuracy rates, and are only applicable for small ranges of data. Thus, to overcome the pitfall, the proposed system lies in performing an encryption based security to the VANET data using the Hybrid HEAECC algorithm and in selecting the optimal path for the travel by the process of Cluster Head (CH) suing meta-heuristic algorithm comprising APSLO algorithm. The further classification of the attack and non-attack in the data are done using the DCBLSTM. The overall model efficacy is evaluated using the measurable and applicable metrics for the model performing the classification of attack and non-attack to the VANET data.