Data Driven Intrusion Detection in Autonomous/Connected Vehicles

Securing autonomous vehicle environments has recently become a hot topic for both industry and academia due to the significant safety and monetary costs associated with security breaches of such environments. This requires different approaches to address the challenges and propose potential solutions at multiple levels of these environments. To that end, machine learning (ML) and blockchain (BC) techniques can play a vital role in ensuring that the safety and security standards are satisfied to protect vehicles from failures that may cause an accident and/or possible attacks. Therefore, this project focuses on exploring the security vulnerabilities associated with the communication technologies used (e.g. short-range and cellular communication technologies) as well as the potential surface attacks associated with the different entities of such environments (e.g. vehicle, controller node, edge node, and access controllers). Moreover, this project investigates the effectiveness and efficiency of ML and BC solutions in addressing and mitigating these vulnerabilities.

Intern: 
MohammadNoor Injadat;Li Yang;Sulaiman Aburakhia
Faculty Supervisor: 
Abdallah Shami
Province: 
Ontario
University: 
Partner University: 
Program: