Autonomous vehicles security: challenges and solutions using blockchain and artificial intelligence

Gueltoum Bendiab, Amina Hameurlaine, Georgios Germanos, Nicholas Kolokotronis, Stavros Shiaeles

Research output: Contribution to journalArticlepeer-review

1220 Downloads (Pure)

Abstract

The arrival of autonomous vehicles (AVs) promises many great benefits, including increased safety and reduced energy consumption, pollution, and congestion. However, these engines have many security and privacy issues that could undermine the expected benefits if not addressed. AVs will provide new opportunities for hackers to carry out malicious attacks, posing a great threat to the future of mobility and data protection. The research trend in this field indicates that combining Blockchain and AI could bring strong protection for AVs against malicious attacks. Blockchain and AI have different working paradigms, but when merged, they can empower each other, and solve many security and privacy issues of AVs. AI can optimise the construction of the Blockchain to make it more efficient, secure and energy-saving, where Blockchain provides data immutability and trust mechanism for AI-based solutions and makes them more transparent, trustful, and explainable. Although some research is being conducted on this area, the topic of applying Blockchain and AI for securing AVs is not deeply investigated. In this paper, we explore the possible application of an amalgamation of Blockchain and AI solutions for securing AVs. We first introduce a classification of security and privacy threats that may arise from the application of AVs. Then, we provide an overview of recent literature regarding Blockchain and AI usage for securing AVs. Finally, we highlight limitations and challenges that may face the integration of Blockchain and AI with AVs based on our systemic review and suggest potential future directions for research in this field.

Original languageEnglish
JournalIEEE Transactions on Intelligent Transportation Systems
Early online date20 Jan 2023
DOIs
Publication statusEarly online - 20 Jan 2023

Keywords

  • Graph neural network
  • human action recognition
  • motion prediction
  • skeleton model

Cite this