Extending Developer Support: Quantum Artificial Intelligence for Automotive Security

With the adoption of advanced technology in the automotive field, managing the risks of attack in modern vehicles becomes essential. Some research works substantially exploit Machine Learning algorithms to identify threats conducted on vehicles, particularly on the Controller Area Network (CAN) bus. Therefore, it is necessary not only to use Intrusion Detection Systems (IDSs) to identify attacks but also to help the engineers in the automotive field understand the dangerousness of the attack and help them resolve the vulnerability. With the increasing attention to Quantum Computing (QC), QC-based Artificial Intelligence algorithms have become very popular among many researchers for improving the prediction and the time performance to identify an attack. This paper proposes a methodology, SeQuADE (Secure Quantum Automotive Development and Engineering), to identify CAN attacks and to support developers by proposing associated automotive vulnerabilities and solutions obtained from National Vulnerability Database (NVD).