Abstract | ||
---|---|---|
The Controller Area Network (CAN) in vehicles provides serial communication between electronic control units that manage engine, transmission, steering and braking. Researchers have recently demonstrated the vulnerability of the network to cyber-attacks which can manipulate the operation of the vehicle and compromise its safety. Some proposals for CAN intrusion detection systems, that identify attacks by detecting packet anomalies, have drawn on one-class classification, whereby the system builds a decision surface based on a large number of normal instances. The one-class approach is discussed in this paper, together with initial results and observations from implementing a classifier new to this field. The Compound Classier has been used in image processing and medical analysis, and holds advantages that could be relevant to CAN intrusion detection.
|
Year | Venue | Field |
---|---|---|
2018 | GECCO (Companion) | Serial communication,CAN bus,Data mining,Anomaly detection,Computer science,Network packet,Image processing,Artificial intelligence,Classifier (linguistics),Decision boundary,Intrusion detection system,Machine learning |
DocType | ISBN | Citations |
Conference | 978-1-4503-5764-7 | 1 |
PageRank | References | Authors |
0.37 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrew Tomlinson | 1 | 1 | 0.37 |
Jeremy W. Bryans | 2 | 175 | 13.88 |
Siraj Ahmed Shaikh | 3 | 30 | 6.65 |