Efficient CAN Dataset Collection Method for Accurate Security Threat Analysis on Vehicle Internal Network

Koh, Yeji; Kim, Seoyeon; Kim, Yoonji; Oh, Insu; Yim, Kangbin

doi:10.1007/978-3-031-08819-3_10

Cited by 7 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its main functions include simulation, test analysis, and development. It can not only simulate and analyze the traditional CAN bus based on the real network environment, but also analyze almost all vehicle network protocols [37], including vehicle Ethernet, so it is widely used by many developers and scholars. We leverage CANoe's powerful capabilities to perform design analysis based on our solutions and SOME/IP protocol specifications.…”

Section: Improvement Scheme Performance Analysis and Methods Comparisonmentioning

confidence: 99%

Security Analysis and Improvement of Vehicle Ethernet SOME/IP Protocol

Tang

Feng

2022

Sensors

View full text Add to dashboard Cite

The combination of in-vehicle networks and smart car devices has gradually developed into Intelligent Connected Vehicles (ICVs). Through the vehicle security protocol, ICVs can quickly realize communication transmission. However, with the more frequent connections between smart in-vehicle devices and the network, the relationship between intelligent cars and external systems is becoming more and more complicated, and in-vehicle networks are gradually facing many security issues. Strengthening the security of in-vehicle protocols has become particularly important. This paper uses the model building method based on the Colored Petri Net (CPN) theory to model the Scalable service-Oriented MiddlewarE over IP (SOME/IP) protocol of the vehicle Ethernet. The security protocol is formally verified and analyzed by combining it with the Dolev–Yao adversary model detection method. After verification, the protocol is subject to three attack vulnerabilities: replay, tampering, and deception. We introduce timestamps and random numbers to strengthen the protocol security. After the final analysis and verification, the improved scheme in this paper can effectively improve the security performance of the protocol.

show abstract

Section: Improvement Scheme Performance Analysis and Methods Comparisonmentioning

confidence: 99%

Security Analysis and Improvement of Vehicle Ethernet SOME/IP Protocol

Tang

Feng

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Although OBD-II is commonly used by researchers to collect data for diagnostic purposes, not all types of data can be collected through this method because not all ECUs are connected to the OBD-II port. In order to collect data from these ECUs, we use a method called ECU direct approach (EDA) [38], which involves collecting data directly from the internal gateway of the vehicle using line-tapping tools. The PEAK CAN system is used as an interfacing device to access the CAN network.…”

Section: Data Collectionmentioning

confidence: 99%

CANPerFL: Improve In-Vehicle Intrusion Detection Performance by Sharing Knowledge

et al. 2023

Self Cite

View full text Add to dashboard Cite

The Controller Area Network (CAN) is a widely used communication protocol in automobiles, but it is vulnerable to various types of attacks. To address this issue, researchers have been exploring the use of intrusion detection systems (IDS) for the CAN bus. Deep learning and machine learning have been proven to be powerful tools for detecting intrusions accurately and quickly. However, deep learning models require large amounts of data to achieve optimal performance, which can be challenging in the case of a CAN bus IDS. To overcome this challenge, we propose a novel machine learning-based IDS called CANPerFL that uses a personalized federated learning scheme to aggregate datasets from different car models. By building a universal model trained on a small amount of data from each manufacturer, we can provide global knowledge that can be transferred to improve the performance of each participant. To demonstrate the efficiency of the proposed model, we collected a real CAN dataset consisting of three different car models: KIA, BMW, and Tesla. The experimental results show that the proposed model increases F1 scores by 4% overall, compared to baselines. Moreover, the proposed system provides significant advantages when the local dataset of each participant is relatively small. According to our experiments, the proposed models can achieve F1 scores of more than 90% with at least 30k training samples on each client. Finally, we show empirically that each participant takes benefits from joining the CANPerFL system.

show abstract