Protecting ECUs and Vehicles Internal Networks

The Automotive Industry is on the verge of digital transformation. The race building fully connected and autonomous cars has begun and it will redefine the way we have been using transportation systems. The goal of connected cars is to provide personalized and safe driving, but connectivity is openi...

Full description

Saved in:
Bibliographic Details
Main Authors: Sharma, Priyanka, Moller, Dietmar P. F.
Format: Conference Proceeding
Language:English
Subjects:
Anomaly Detection
Automobiles
CAN-Bus
Connected Cars
ECUs
IDPS
Intrusion detection
Machine learning
Protocols
Recurrent neural networks
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Automotive Industry is on the verge of digital transformation. The race building fully connected and autonomous cars has begun and it will redefine the way we have been using transportation systems. The goal of connected cars is to provide personalized and safe driving, but connectivity is opening the doors for cyber-attacks. Control Area Network (CAN)-bus is a serial car bus network that connects Electronic Control Units (ECUs), sensors and actuators in a system or subsystem for control applications. Thousands of signals are recorded on the CAN-Bus which can give almost real-time information about the car, driver and the surroundings. This paper proposes a conceptual approach for intrusion detection and prevention systems (IDPSs) for connected cars and an overview of machine learning algorithms for anomaly detection as part of intrusion detection.
ISSN:2154-0373
DOI:10.1109/EIT.2018.8500295