Chinese Remainder Cryptosystem-Based Multilayer Perceptron Signcryption for Secure Vehicular Communication

Vehicular ad-hoc networks (VANETs) are significant network environments for communication between vehicles to efficiently address the issues concerning traffic safety, traffic management and circumventing congestion. Signcryption has been employed in VANET owing to the reason that both signing and encryption are done simultaneously, therefore minimising computational cost. However, communication costs and verification processing time were increased. To address this issue, a Chinese remainder cryptosystem-based multilayer perceptron certificateless signcryption (CRC-MPCS) for secure data communication in VANET is proposed. The deep learning framework employing a multilayer perceptron possesses three layers. VANET vector parameters are provided as input to the input layer. The first hidden layer performs the sender vehicle node key generation, and the second hidden layer performs the receiver vehicle node credential generation. Finally, the output layer, along with the weight updates for each epoch and rectified linear unit (ReLU) activation, certificateless cryptosystem (CLC), performs secure vehicular communication. The proposed CRC-MPCS method reduces signcryption verification processing time and improves data confidentiality, data integrity, authentication accuracy and communication cost compared to conventional methods.