| KEYWORD |
Microelectronics
AI-based Cyber Attack Detection for Connected Vehicles
Thesis in external company
keywords CYBERSECURITY, MACHINE LEARNING, PATTERN RECOGNITION
Reference persons LUCIANO LAVAGNO
External reference persons Michele Crepaldi, Reply Torino
Research Groups Microelectronics
Thesis type APPLIED RESEARCH
Description The rise of connected vehicles has increased their vulnerability to cyber attacks, which can be potentially
dangerous. To mitigate these risks, it is important to have real-time detection systems in place. The thesis
project aims to address this issue by developing a compact and efficient AI model that can detect ongoing
cyber attacks that target combustion engine operating parameters directly on the vehicle. This will
significantly improve the safety of connected vehicles by allowing for an immediate response to such threats.
The model will be optimized for the limited computational resources of the vehicle's Engine Control Unit
(ECU) to ensure its seamless integration with the vehicle's systems.
Required skills Python programming, some knowledge of Machine Learning
Notes The student will be involved in:
❑ SW and HW requirements definition
❑ Database setup: nominal engine operating conditions and attack examples
❑ Design and development of attack detection AI algorithm
❑ On edge performance optimization and miniaturization
❑ Model validation and testing (benchmarking)
Deadline 11/10/2024
PROPONI LA TUA CANDIDATURA