Detecting CAN Bus Intrusion by Applying Machine Learning Method to Graph Based Features

Refat, Rafi Ud Daula; Elkhail, Abdulrahman Abu; Hafeez, Azeem; Malik, Hafiz

doi:10.1007/978-3-030-82199-9_49

Cited by 18 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of Dataset 2, DT achieves a higher level of accuracy by 1.74% compared to [ 21 ]. While compared to [ 31 ], the accuracy that has been achieved using KNN for Dataset 1 is 1.74% greater than that of accuracy achieved in [ 32 ]. In addition, the F1 score of SVM and KNN of our proposed study is higher than [ 32 ] for both datasets.…”

Section: Performance Analysis and Future Recommendationsmentioning

confidence: 82%

“…While compared to [ 31 ], the accuracy that has been achieved using KNN for Dataset 1 is 1.74% greater than that of accuracy achieved in [ 32 ]. In addition, the F1 score of SVM and KNN of our proposed study is higher than [ 32 ] for both datasets. However, for the accuracy of SVM with Dataset 2 in our proposed study, it is a little bit lower than [ 21 , 32 ].…”

Section: Performance Analysis and Future Recommendationsmentioning

confidence: 82%

“…To handle problems of classification and regression, KNN is utilized as a supervised ML method [ 32 ]. For classification, at first, it calculates the number of nearest neighbors.…”

Section: Methodsmentioning

confidence: 99%

“…In a vehicular network, ECUs can communicate with other ECUs. Each ECU consists of a CAN controller, CAN transceiver, and a microcontroller [ 32 ]. Several researchers have sent out fake messages to different ECUs utilizing the in-vehicle networks, peruse ECU memory, and ECU security keys.…”

Section: Background and Critical Review Of The Existing Research Gapmentioning

confidence: 99%

“…The differential voltages are outputs and consist of 2 states of voltages, dominant (or logical 0) and recessive (logical 1). The two pins on the CAN transceiver are connected directly to the bus, allowing the ECU to transmit and receive a message from the bus [ 32 ].…”

Section: Background and Critical Review Of The Existing Research Gapmentioning

confidence: 99%

See 4 more Smart Citations

Intrusion Detection in Vehicle Controller Area Network (CAN) Bus Using Machine Learning: A Comparative Performance Study

Bari

Yelamarthi

Ghafoor

2023

Sensors

View full text Add to dashboard Cite

Electronic Control Units (ECUs) have been increasingly used in modern vehicles to control the operations of the vehicle, improve driving comfort, and safety. For the operation of the vehicle, these ECUs communicate using a Controller Area Network (CAN) protocol that has many security vulnerabilities. According to the report of Upstream 2022, more than 900 automotive cybersecurity incidents were reported in 2021 only. In addition to developing a more secure CAN protocol, intrusion detection can provide a path to mitigate cyberattacks on the vehicle. This paper proposes a machine learning-based intrusion detection system (IDS) using a Support Vector Machine (SVM), Decision Tree (DT), and K-Nearest Neighbor (KNN) and investigates the effectiveness of the IDS using multiple real-world datasets. The novelty of our developed IDS is that it has been trained and tested on multiple vehicular datasets (Kia Soul and a Chevrolet Spark) to detect and classify intrusion. Our IDS has achieved accuracy up to 99.9% with a high true positive and a low false negative rate. Finally, the comparison of our performance evaluation outcomes demonstrates that the proposed IDS outperforms the existing works in terms of its liability and efficiency to detect cyber-attacks with a minimal error rate.

show abstract

Section: Performance Analysis and Future Recommendationsmentioning

confidence: 82%

Section: Performance Analysis and Future Recommendationsmentioning

confidence: 82%

“…To handle problems of classification and regression, KNN is utilized as a supervised ML method [ 32 ]. For classification, at first, it calculates the number of nearest neighbors.…”

Section: Methodsmentioning

confidence: 99%

Section: Background and Critical Review Of The Existing Research Gapmentioning

confidence: 99%

Section: Background and Critical Review Of The Existing Research Gapmentioning

confidence: 99%

See 3 more Smart Citations

Intrusion Detection in Vehicle Controller Area Network (CAN) Bus Using Machine Learning: A Comparative Performance Study

Bari

Yelamarthi

Ghafoor

2023

Sensors

View full text Add to dashboard Cite

show abstract

Machine Learning for Automotive Cybersecurity: Challenges, Opportunities and Future Directions

Refat

Elkhail²,

Malik³

2022

AI-enabled Technologies for Autonomous and Connected Vehicles

View full text Add to dashboard Cite

Fingerprinting ECUs to Implement Vehicular Security for Passenger Safety Using Machine Learning Techniques

Bellaire

Bayer²,

Hafeez³

et al. 2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Detecting CAN Bus Intrusion by Applying Machine Learning Method to Graph Based Features

Cited by 18 publications

References 35 publications

Intrusion Detection in Vehicle Controller Area Network (CAN) Bus Using Machine Learning: A Comparative Performance Study

Intrusion Detection in Vehicle Controller Area Network (CAN) Bus Using Machine Learning: A Comparative Performance Study

Machine Learning for Automotive Cybersecurity: Challenges, Opportunities and Future Directions

Fingerprinting ECUs to Implement Vehicular Security for Passenger Safety Using Machine Learning Techniques

Contact Info

Product

Resources

About