Privacy-Preserving Attribute-Based Access Control Scheme With Intrusion Detection and Policy Hiding for Data Sharing in VANET

Vehicle ad-hoc network (VANET) plays an important role in improving traffic management and driving safety. Data sharing in VANET can be achieved using such communications as Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Cloud (V2C). However, due to the openness of VANET, if an adversary can access shared data without authorization, it will seriously threaten vehicle safety and user privacy, and bring great challenges to data sharing. Therefore, it is necessary to establish an efficient access control scheme for secure data sharing in cloud-assisted VANET. Attribute-based encryption (ABE) can achieve fine-grained access control. However, the traditional access control schemes for VANET rarely consider attack detection and policy privacy protection, and the efficiency is low. Therefore, this article proposes an ABE access control scheme combining intrusion detection and policy hiding, which can filter malicious users and realize secure and efficient data access control under privacy protection. Firstly, partial policy hiding is realized by anonymizing policy attribute values. Secondly, a deep learning model is constructed by sparse stacked autoencoder (SSAE) and a three-layer bidirectional long short-term memory (BiLSTM) network to detect user data access request packets and effectively filter malicious users. Thirdly, based on the edge structure, complex operations are delegated to the road side unit (RSU) with verifiable outsourced encryption and decryption to reduce the computational and storage overhead of the vehicle. Finally, the security of the proposed ABE scheme is proved. In addition, experimental results show that compared with other schemes, the proposed scheme has higher efficiency while ensuring security.