Anomaly-Based Intrusion Detection for a Vehicle Can Bus: A Case for Hyundai Avante Cn7

Abstract

Flooding, spoofing, replay, and fuzzing are common in various types of attacks faced by enterprises and various network systems. In-vehicle network systems are not immune to attacks and threats. Intrusion detection systems using different algorithms are proposed to enhance the security of the in-vehicle network. We use a dataset provided and collected in "Car Hacking: Attack and Defense Challenge" during 2020. This dataset has been realized by the organizers of the challenge for security researchers. With the aid of this dataset, the work aimed to develop attack and detection techniques of Controller Area Network (CAN) using different algorithms such as support vector machine and Feedforward Neural Network. This research work also provides a comparison of the rendering of these algorithms. Based on experimental results, this work will help future researchers to benchmark their results for the given dataset. The results obtained in this work show that the model selection does not depend only on the model's accuracy that is explained by the accuracy paradox. Therefore, for the overall result accuracy of 62.65%, they show that the support vector machine presents the most satisfying output in terms of precision and recall. The Radial basis kernel gives 65% and 67% precision for fuzzing and flooding and the recall of 64% and 100% for replay and spoofing, respectively.

Development of a Malicious Network Traffic Intrusion Detection System Using Deep Learning

“…After carrying out model training and validation, we evaluate the performance of the model using standard performance metrics such as accuracy, precision, recall, and F1-score (using Eqs. ( 1)-( 4)) [35,36]. 5, and it shows that, across the three models for the two experimental setups, LSTM achieve the best performance, particularly in experimental setup one, with an accuracy of 98.09%, precision of 98.14%, F1-score of 98.09%, and recall of 98.05%.…”

Congestion Intrusion Detection-Based Method for Controller Area Network Bus: A Case for KIA SOUL Vehicle

“…According to the result provided in Okokpujie et al [20], the authors used the Support Vector Machine (SVM) model and the DeepFNN. After the performance evaluation of both models, the classification report revealed that the Radial basis kernel of SVM provided satisfactory results in terms of Fmeasures in the proportion of 64% and 80% for fuzzing and flooding attacks respectively.…”

“…Considering models are not always suitable for all applications, the technique used in this work differs from that of the authors in Lee et al [19], who did not adopt a machine learning approach. On the other hand, in Okokpujie et al [20], DeepFNN and SVM models were used for the classification. However, all features were used as one.…”

“…Okokpujie et al [20] developed an anomaly-based detection technique of a CAN using two different models, mainly the Support Vector Machine (SVM) model and the Deep Feedforward Neural Network (DeepFNN) model. The authors presented a comparison between the results of each model.…”

Development of an Affordable Real-Time IoT-Based Surveillance System Using ESP32 and TWILIO API

“…Traditional surveillance systems predominantly comprised analogue cameras connected via coaxial cables. However, with evolving technology, Closed-Circuit Television (CCTV) systems continue to be a staple in maintaining public order and security [2][3][4][5]. In response to cost and performance considerations, a shift towards digital systems has been observed, with current data transmission relying on Internet Protocol (IP) [6,7].…”