<p>The emerged development in the sector of the Internet of Vehicles (IoV) has offered various satisfactions to the candidates because of its ability to help the vehicles with the transmission of wireless data. The data exchange between the vehicle nodes is complex because of the speed and varying topologies, unpredictable network conditions, and large node motilities. Locating a private secure entity to distribute and store the messages between the data nodes is also one of the complex works. IoV is vulnerable to multiple privacy and security threats like unauthorized location tracking and hijacking of smart vehicles. To penalize and detect malicious nodes, traceability is an enhancing crucial factor of vehicular transmissions. In addition, attaining both traceability and privacy can also be a hard task. To rectify these hurdles, this work suggested a smart contract-aided blockchain-based secure, efficient, and anonymous conditional privacy-preserving and authentication mechanism with machine learning for IoV networks. Initially, the blockchain stores the data at different blocks, and then a machine learning algorithm is demonstrated to detect malware activities. Machine learning with smart contract-adopted blockchain technology helps to transmit secure information in IoV. The features are selected using the developed Hybrid Adaptive Network (HANet), where the Multi-Layer Perceptron (MLP) and Ridge classifiers for detecting malicious attacks. Moreover, the parameters present in the Hybrid Adaptive Network are optimized through offered Opposition Beluga Whale Optimization (OBWO). The experimental outcomes are validated with the traditional machine learning-based data authentication mechanisms in IoV to examine the effectiveness of the developed model.</p>