ALICIA: Applied Intelligence in blockchain based VANET: Accident Validation as a Case Study

【Author】 Maskey, Shirshak Raja; Badsha, Shahriar; Sengupta, Shamik; Khalil, Ibrahim

【Source】INFORMATION PROCESSING & MANAGEMENT

【影响因子】7.466

【Abstract】In a connected vehicle application, the driver heavily depends on the messages, such as accident notification, collision warning, brake warning, etc., generated by the vehicle. These messages, which are generated by On-Board Units (OBU) can be used by an attacker to distract the driver or change the driving behavior to fulfill the attacker's intentions. These generations of false messages are termed under illusion attacks. These types of attacks can be deterred by using blockchain-based architecture, which requires consensus to validate the generated messages. While the implementation of blockchain technology in connected vehicles is increasing, it is facing several vulnerabilities and threats from malicious nodes, anomalous data, and imperfect consensus mechanisms. These vulnerabilities in the system are majorly caused by malicious nodes. The generated false data can be injected at any section of the network, and not only by connected vehicles but also by endorsing Road Side Units (RSUs). These vulnerabilities can be checked to a great extent through the Miner Node Selection (MNS) process in blockchain-based systems. The MNS process selects a specific set of RSUs from all RSUs in a vehicular network (VANET) to run the consensus process. To overcome that goal, we propose ALICIA (AppLied Intelligence in bloCkchaIn vAnet) where we have used the Artificial Neural Network (ANN) to select when and which node to exclude during the consensus process. Similarly, we have also proposed our Accident detection and validation system where we detect and validate an accident, and send the data to ALICIA to perform MNS. We have used Hyperledger Fabric (HF), a blockchain platform developed as a part of the Hyperledger Project, to implement our architecture, which uses the Practical Byzantine Fault Tolerance (PBFT) method to reach consensus for it does not require high computation power to add transactions to the blockchain.

【Keywords】Blockchain; Hyperledger Fabric; Artificial neural networks; Miner node selection; VANET systems

【发表时间】2021 MAY

【收录时间】2022-01-02

【文献类型】

【主题类别】

--