Application of Controller Area Network (CAN) bus anomaly detection based on time series prediction

Qin, Hongmao; Yan, Mengru; Ji, Haojie

doi:10.1016/j.vehcom.2020.100291

Cited by 41 publications

(34 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, The ML&DL methods mentioned above differ in the mode of selecting the detection domain of a message, typically the detection arbitration domain proposed by Song et al [11], the detection data domain proposed by Qin et al [12], and the spatial-temporal feature extraction proposed by Tariq et al [25], which is similar to our work. In a nutshell, traditional methods based on specification, fingerprint, and statistical, have limitations in terms of reliance on anomaly feature libraries, message frequency, message time domain, and fingerprint information.…”

Section: Intrusion Detection Model Based On Deep Learningsupporting

confidence: 72%

“…In 2019, Pawelec et al [26] proposed a 3-layer LSTM neural network to predict the data payload for each CAN ID, which avoided reverse engineering proprietary encoding. Similarly, Qin et al [12] also implemented anomaly detection for CAN bus based on timing features by LSTM and re-considered two data formats of CAN frames. Like Pawelec's method, both are implemented at the CAN bits level, but they both consider only timing characteristics and have relatively poor detection performance.…”

Section: Intrusion Detection Model Based On Deep Learningmentioning

confidence: 99%

“…Simultaneously, inadequate feature extraction and its complex network structure and more parameters, also are pending breakthroughs [11]. To address such issues, variants of IDS based on deep learning have been proposed in recent years [11], [12], [13]. However, these variants of IDS merely consider the partial features, either time-series of CAN ID or CAN data field.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

STC-IDS: Spatial-Temporal Correlation Feature Analyzing based Intrusion Detection System for Intelligent Connected Vehicles

Han,

Cheng,

Zhang

2022

Preprint

View full text Add to dashboard Cite

Intrusion detection is an important defensive measure for the security of automotive communications. Accurate frame detection models assist vehicles to avoid malicious attacks. Uncertainty and diversity regarding attack methods make this task challenging. However, the existing works have the limitation of only considering local features or the weak feature mapping of multi-features. To address these limitations, we present a novel model for automotive intrusion detection by spatial-temporal correlation features of in-vehicle communication traffic (STC-IDS). Specifically, the proposed model exploits an encodingdetection architecture. In the encoder part, spatial and temporal relations are encoded simultaneously. To strengthen the relationship between features, the attention-based convolution network still captures spatial and channel features to increase the receptive field, while attention-LSTM build important relationships from previous time series or crucial bytes. The encoded information is then passed to detector for generating forceful spatial-temporal attention features and enabling anomaly classification. In particular, single-frame and multi-frame models are constructed to present different advantages respectively. Under automatic hyperparameter selection based on Bayesian optimization, the model is trained to attain the best performance. Extensive empirical studies based on a real-world vehicle attack dataset demonstrate that STC-IDS has outperformed baseline methods and cables fewer false-positive rates while maintaining efficiency.

show abstract

Section: Intrusion Detection Model Based On Deep Learningsupporting

confidence: 72%

Section: Intrusion Detection Model Based On Deep Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

STC-IDS: Spatial-Temporal Correlation Feature Analyzing based Intrusion Detection System for Intelligent Connected Vehicles

Han,

Cheng,

Zhang

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Model-based approaches mostly use algorithms that are very accurate, such as machine learning schemes [32], whereas the approaches based on data analysis usually used statistical measurements. On urban roads, anomalies cause discomfort to drivers and have a negative impact on traffic efficiency [6]. When traffic accidents occur and there is congestion, traffic flow is abnormal [26].…”

Section: Related Workmentioning

confidence: 99%

Detection of Road Traffic Anomalies Based on Computational Data Science

Raiyn

2022

Preprint

View full text Add to dashboard Cite

The development of 5G has enabled the autonomous vehicles (AVs) to have full control over all functions. The AV acts autonomously and collects travel data based on various smart devices and sensors, with the goal of enabling it to operate under its own power. However, the collected data is affected by several sources that degrade the forecasting accuracy. To manage large amounts of traffic data in different formats, a computational data science approach (CDS) is proposed. The computational data science scheme introduced to detect anomalies in traffic data that negatively affect traffic efficiency. The combination of data science and advanced artificial intelligence techniques, such as deep leaning provides higher degree of data anomalies detection which leads to reduce traffic congestion and vehicular queuing. The main contribution of the CDS approach is summarized in detection of the factors that caused data anomalies early to avoid long- term traffic congestions. Moreover, CDS indicated a promoting results in various road traffic scenarios.

show abstract

“…While time series are widely used in various fields, long- and short-term memory models are preferred for deep learning analysis of time series. For example, Qin et al [ 23 ] used time series to create a model used to detect abnormal behavior in controller area network (CAN) buses under tampering attacks. Tulensalo et al [ 32 ] used local weather data to determine total local grid transmission losses.…”

Section: Introductionmentioning

confidence: 99%

Analysis of agricultural exports based on deep learning and text mining

Hsu

2022

J Supercomput

View full text Add to dashboard Cite

Agricultural exports are an important source of economic profit for many countries. Accurate predictions of a country’s agricultural exports month on month are key to understanding a country’s domestic use and export figures and facilitate advance planning of export, import, and domestic use figures and the resulting necessary adjustments of production and marketing. This study proposes a novel method for predicting the rise and fall of agricultural exports, called agricultural exports time series-long short-term memory (AETS-LSTM). The method applies Jieba word segmentation and Word2Vec to train word vectors and uses TF-IDF and word cloud to learn news-related keywords and finally obtain keyword vectors. This research explores whether the purchasing managers’ index (PMI) of each industry can effectively use the AETS-LSTM model to predict the rise and fall of agricultural exports. Research results show that the inclusion of keyword vectors in the PMI values of the finance and insurance industries has a relative impact on the prediction of the rise and fall of agricultural exports, which can improve the prediction accuracy for the rise and fall of agricultural exports by 82.61%. The proposed method achieves improved prediction ability for the chemical/biological/medical, transportation equipment, wholesale, finance and insurance, food and textiles, basic materials, education/professional, science/technical, information/communications/broadcasting, transportation and storage, retail, and electrical and machinery equipment categories, while its performance for the electrical and optical categories shows improved prediction by combining keyword vectors, and its accuracy for the accommodation and food service, and construction and real estate industries remained unchanged. Therefore, the proposed method offers improved prediction capacity for agricultural exports month on month, allowing agribusiness operators and policy makers to evaluate and adjust domestic and foreign production and sales.

show abstract

Application of Controller Area Network (CAN) bus anomaly detection based on time series prediction

Cited by 41 publications

References 7 publications

STC-IDS: Spatial-Temporal Correlation Feature Analyzing based Intrusion Detection System for Intelligent Connected Vehicles

STC-IDS: Spatial-Temporal Correlation Feature Analyzing based Intrusion Detection System for Intelligent Connected Vehicles

Detection of Road Traffic Anomalies Based on Computational Data Science

Analysis of agricultural exports based on deep learning and text mining

Contact Info

Product

Resources

About