Controller Area Network Data Research Articles

Windowed Hamming Distance-Based Intrusion Detection for the CAN Bus

The use of a Controller Area Network (CAN) bus in the automotive industry for connecting electronic control units (ECUs) poses security vulnerabilities due to the lack of built-in security features. Intrusion Detection Systems (IDSs) have emerged as a practical solution for safeguarding the CAN bus. However, developing an effective IDS for in-vehicle CAN buses encounters challenges in achieving high precision for detecting attacks and meeting real-time requirements with limited computational resources. To address these challenges, we propose a novel method for anomaly detection on CAN data using windowed Hamming distance. Our approach utilizes sliding windows and Hamming distance to extract features from time series data. By creating benchmark windows that span at least one cycle of data, we compare newly generated windows with recorded benchmarks using the Hamming distance to identify abnormal CAN messages. During the experimental phase, we conduct extensive testing on both the public car-hack dataset and a proprietary dataset. The experimental results indicate that our method achieves an impressive accuracy of up to 99.67% in detecting Denial of Service (DoS) attacks and an accuracy of 98.66% for fuzzing attacks. In terms of two types of spoofing attacks, our method achieves detection accuracies of 99.48% and 99.61%, respectively, significantly outperforming the methods relying solely on the Hamming distance. Furthermore, in terms of detection time, our method significantly reduces the time consumption by nearly 20-fold compared to the approach using deep convolutional neural networks (DCNN), decreasing it from 6.7 ms to 0.37 ms.

Single-Frame-Based Data Compression for CAN Security

To authenticate a controller area network (CAN) data frame, a message authentication code (MAC) must be sent along with the CAN frame, but there is no space reserved for the MAC in the CAN frame. Recently, difference-based compression (DBC) algorithms have been used to create a space inside the frame. DBC has the advantage of being very efficient, but its drawback is that, if an error occurs in one frame, the effects of that error propagate to subsequent frames. In this paper, a CAN data compression algorithm is proposed that compresses the current frame without relying on previous frames. Therefore, an error generated in one frame cannot be propagated to subsequent frames. In addition, a CAN signal grouping technique is proposed based on entropy analysis. To efficiently authenticate CAN frames, the length of the compressed data must be 4 bytes or less (4BL). Simulation shows that the 4BL-compression ratio of a Kia Sorento vehicle is 99.36% in the DBC method, but 100% in the proposed method. In an LS Mtron tractor, the 4BL-compression ratio is 98.58% in the DBC method, but 100% in the proposed method. In addition, the execution time of the proposed compression algorithm is only 27.39% of that of the DBC algorithm. The results show that the proposed algorithm has better compression characteristics for CAN security than the DBC algorithms.

Can-train-and-test: A curated CAN dataset for automotive intrusion detection

When it comes to in-vehicle networks (IVNs), the controller area network (CAN) bus dominates the market; automobiles manufactured and sold worldwide depend on the CAN bus for safety-critical communications between various components of the vehicle (e.g., the engine, the transmission, the steering column). Unfortunately, the CAN bus is inherently insecure; in fact, it completely lacks controls such as authentication, authorization, and confidentiality (i.e., encryption). Therefore, researchers have travailed to develop automotive security enhancements. The automotive intrusion detection system (IDS) is especially popular in the literature—due to its relatively low cost in terms of money, resource utilization, and implementation effort. That said, developing and evaluating an automotive IDS is often challenging; if researchers do not have access to a test vehicle, then they are forced to depend on publicly available CAN data—which is not without limitations. Lack of access to adequate CAN data, then, becomes a barrier to entry into automotive security research.We seek to lower that barrier to entry by introducing a new CAN dataset to facilitate the development and evaluation of automotive IDSs. Our datasets—dubbed can-dataset, can-log, can-csv, can-ml, and can-train-and-test—provide CAN data from four different vehicles produced by two different manufacturers. The attack captures for each vehicle model are equivalent, enabling researchers to assess the ability of a given IDS to generalize to different vehicle models and even different vehicle manufacturers. Our datasets contain replayable .log files as well as labeled and unlabeled .csv files, thereby meeting a variety of development and evaluation needs. In particular, the can-train-and-test dataset offers nine unique attacks, ranging from denial of service (DoS) to gear spoofing to standstill; as such, researchers can select a subset of the attacks for training and save the remainder for testing in order to assess a given IDS against unseen attacks. Many of our attacks, particularly the spoofing-related attacks, were conducted during live, on-the-road experiments with real vehicles. These attacks have known physical impacts. As a benchmark, we pit a number of machine learning IDSs against our dataset and analyze the results. We present our datasets—especially can-train-and-test—as a contribution to the existing catalogue of open-access datasets in hopes of filling in the gaps left by those datasets.

Analysis of 38 kW class agricultural tractor engine load rate according to agricultural operation

This study was conducted to analyze the engine load ratio of a 38 kW agricultural tractor to calculate national emissions. Engine output was calculated using engine CAN (Controller area network) data measured through a load measurement system. In this study, plow tillage (PT) and rotary tillage (RT), which are the main agricultural tasks of small and medium horsepower tractors, were selected and performed three times for each stage. The engine load ratio was calculated as the ratio of the engine power generated during work and the engine rated power, and weights (25% each for PT M1, PT M2, RT L3, and RT L4) according to the agricultural work ratio were applied. The engine load ratio was found to be an average of 0.68 and 0.75 for the M1 and M2 stages of plow tillage work, respectively, and an average of 0.57 and 0.65 for the L3 and L4 stages of rotary tillage work, respectively. The weighted load ratio was 0.17, 0.19, 0.14, and 0.16 for plow tillage operation M1, M2, and rotary tillage operation L3 and L4, respectively. The integrated load factor was found to be 0.66, which is approximately 1.38 higher than the current domestic load factor of 0.48.

Optimal Control Design and Online Controller-Area-Network Bus Data Analysis for a Light Commercial Hybrid Electric Vehicle

In this article, a hybrid powertrain for the Volkswagen (VW) Crafter is designed using the Model-In-The-Loop (MIL) method. An enhanced Proportional-Integral (PI) control technique based on integral cost functions is developed by carrying out a time-based simulation in MATLAB/Simulink software to realize the optimal fuel economy of the vehicle. Moreover, a comparative study is conducted between the vehicle’s hybrid and pure electric versions to assess the optimal battery energy consumption per unit distance traveled. Communication within our vehicles’ Electronic Control Units (ECUs) is facilitated by a message-based protocol called a Controller Area Network (CAN). Consequently, this paper presents an online CAN Bus data analysis using the Hardware-In-The-Loop (HIL) method. This method uses a standard frame, J1939 CAN protocol, implemented with Net CAN Plus 110 hardware. A graphical user interface is developed on a host Personal Computer (PC) using LabVIEW for decoding the acquired raw CAN data to physical values. The simulation results reveal that the proposed controller is promising and suitable for realizing optimal performance over the HIL method.

CANLay: A Network Virtualized Testbed for Vehicle Systems – Improving System Integration and Verification Efforts

AbstractIntegration and Verification activities for cyber physical system networks is a complex task requiring multiple iterations of hardware and software configurations and topologies. Such testing is crucial for the system's functionality, safety, and security during operation. A proficient approach to swiftly generate various testing setups is to employ a software‐defined system, vehicle in this case, and encapsulate in‐vehicle networking messages in a switched packet network, like Ethernet. This paper introduces CANLay, the networking foundation of a software‐defined vehicle that serves as a virtualized test bed for in‐vehicle network examination. CANLay carries controller area network data and sensor signals originating from vehicle control units and simulator systems. It functions as a communication medium between a vehicle simulator and real‐world electronic control units situated on distinct network segments. CANLay's efficacy is demonstrated for heavy vehicle network performance testing in a versatile digital engineering environment, facilitating streamlined system integration and verification efforts.

Performance Enhancement of CAN/Ethernet Automotive Gateway with a CAN Data Reduction Algorithm

Data reduction (DR) techniques for the controller area network (CAN) are being developed to reduce the increased bus load caused by the growing number of electronic control units (ECUs) and automotive software complexity in modern automobiles. DR techniques enable the transmission of the same information with less bandwidth, effectively reducing the busload in CAN-based networks. Modern vehicles are composed of various in-vehicle network (IVN) protocols, such as CAN, local interconnect network (LIN), and Ethernet. However, existing DR techniques only consider the communication between CAN nodes. The application of DR techniques to a CAN bus may lead to compatibility issues when communicating with heterogeneous IVN protocols. This paper proposed a CAN/Ethernet gateway system for seamless communication with CAN DR. The proposed gateway system was implemented on a TC275-based embedded system, and its performance was evaluated and analyzed. The experimental results revealed that CAN DR compression effectively improves both the CAN bus load and end-to-end processing time of the gateway system. The CAN bus load was reduced by up to 33.68%, and the average end-to-end processing time was reduced to 336 μs.

Robust Certificateless Authentication Protocol for the SAE J1939 Commercial Vehicles Bus

Authentication for controller area network (CAN) buses in an intra-vehicular network involving electronic control units (ECUs) is a challenging factor. The Society of Automotive Engineers standard (SAE J1939) incorporating the ISO 11898-1 specification for the data link and physical layers of the standard CAN and CAN-flexible data rate (CAN-FD) handles communication among ECUs. The SAE J1939 is vulnerable to attacks, namely replay, masquerading and machine-in-the-middle (MITM) attacks. To prevent such attacks, there exist protocol suites for resource-constrained and resource-unconstrained nodes proposed in the literature which are not formally analysed. We formally analyse one of the comprehensive protocol suites using the state-of-the-art Tamarin automated software validation tool. The analysis reveals that the protocols have a vulnerability that can be exploited by replay attack. The identified replay attack prevents further frame authentication. To mitigate the identified attacks, we propose two new authentication protocols. At first, we propose one pass authentication protocol for computationally restricted nodes. For nodes that are not restricted computationally, we present a certificateless signature-based authentication protocol. Additionally, we present a new certificateless key insulated manageable signature (CL-KIMS) scheme for the signature-based authentication protocol. CL-KIMS ensures key insulation and random access key update properties. CL-KIMS scheme assures a novel property, known as self-healing property. The security of the proposed protocol suite and the signature scheme is formally analysed using the random oracle model (ROM). Especially, CL-KIMS scheme is shown to be provably secure in the ROM against Type-I and Type-II adversaries. We use the Tamarin tool to verify mutual authentication, session key security, known key secrecy and forward security. A detailed performance comparison shows that compared with the existing protocol suites, the proposed protocol suite has lesser communication overhead and ensures robust security. Our simulation study in Matlab further reveals that the key exchange protocols in the proposed protocol suite are efficient with lesser total message delay than its counterpart protocols.

MAC-Based Compression Ratio Improvement for CAN Security

Information security in a controller area network (CAN) is becoming more important as the connections between a vehicle’s internal and external networks increase. Encryption and authentication techniques can be applied to CAN data frames to enhance security. To authenticate a data frame, a message authentication code (MAC) needs to be transmitted with the CAN data frame. Therefore, space for transmitting the MAC is required within the CAN frame. Recently, the Triple ID algorithm has been proposed to create additional space in the data field of the CAN frame. The Triple ID algorithm ensures every CAN frame is authenticated by at least 4 bytes of MAC without changing the original CAN protocol. However, since the Triple ID algorithm uses six header bits, there is a problem associated with low data compression efficiency. In this paper, we propose an algorithm that can remove up to 15 bits from frames compressed with the Triple ID algorithm. Through simulation using CAN signals of a Kia Sorento vehicle and an LS Mtron tractor, we show that the generation of frames containing compressed messages of 4 bytes or more is reduced by up to 99.57% compared to the Triple ID method.

Estimating Battery Size Requirements for Tractor Electrification of Row-Crop Planting Operations

Highlights Calculate and compare engine power needed for row-crop planting from ASAE standards and reported CAN data. Estimate energy requirements and the equivalent electric battery’s volume and mass for row-crop tractor. Discuss the feasibility for electrification of a fully electric row-crop tractor. Abstract. Power sources such as batteries, used for both on-road and off-road vehicles, are advancing at a rapid pace. Electric batteries are becoming more power dense, thus allowing them to be used as a power source to replace previous diesel or gasoline-powered systems. Efforts are underway to transition off-road agricultural vehicles from Internal Combustion Engine (ICE) vehicles to electric vehicles (EVs); however, the energy requirements of typical agricultural field operations need to be fully understood before such a transition can occur. Theoretical prediction equations available in the American Society of Agricultural and Biological Engineers (ASABE) standards or the use of engine load data from a tractor’s Controller Area Network (CAN) bus are two methods for determining the energy demands of implements on tractors. In this study, tractor CAN bus data was collected from multiple no-till corn planting operations to estimate the energy requirements of the planting operation in kWh. The estimated energy requirement was used to determine the equivalent physical mass and volume of a lithium-ion battery needed to power a hypothetical fully electric tractor for comparable planting operations. The estimated battery capacities using the worst-case field-use scenario in this study were 1117 kWh for operating a 16-row planter to plant 68 ha (168 acre) in a day at an average ground speed of 8.6 km h-1 (5.4 mph) for 14 hours, and 2658 kWh for operating a 48-row planter to plant 158 ha (391 acre) in a day at an average ground speed of 8.9 km h-1 (5.6 mph) for 15 hours. Given the current battery energy density requirements, the equivalent battery masses and volumes were found to be 5,319 kg and 3.33 m3, 12,657 kg and 7.93 m3, for 16-row planter and 48-row planter, respectively. These high kWh estimates needed to power future fully-electric tractor power units are based on worst-case scenarios that could be encountered in real field operations that use wide planters over long operating hours. Keywords: Battery, Controller Area Network, Electric Vehicles, Electrification, No-till, Planting, Row-crop, Tractor.

In-Vehicle Data for Predicting Road Conditions and Driving Style Using Machine Learning

Many network protocols such as Controller Area Network (CAN) and Ethernet are used in the automotive industry to allow vehicle modules to communicate efficiently. These networks carry rich data from the different vehicle systems, such as the engine, transmission, brake, etc. This in-vehicle data can be used with machine learning algorithms to predict valuable information about the vehicle and roads. In this work, a low-cost machine learning system that uses in-vehicle data is proposed to solve three categorization problems; road surface conditions, road traffic conditions and driving style. Random forests, decision trees and support vector machine algorithms were evaluated to predict road conditions and driving style from labeled CAN data. These algorithms were used to classify road surface condition as smooth, even or full of holes. They were also used to classify road traffic conditions as low, normal or high, and the driving style was classified as normal or aggressive. Detection results were presented and analyzed. The random forests algorithm showed the highest detection accuracy results with an overall accuracy score between 92% and 95%.

Illegal Intrusion Detection for In-Vehicle CAN Bus Based on Immunology Principle

The controller area network (CAN) bus has become one of the most commonly used protocols in automotive networks. Some potential attackers inject malicious data packets into the CAN bus through external interfaces for implementing illegal operations (intrusion). Anomaly detection is a technique for network intrusion detection which can detect malicious data packs by comparing the normal data packets with incoming data packets obtained from the network traffic. The data of a normal network is in a symmetric and stable state, which will become asymmetric when compromised. Considering the in-vehicle network, the CAN bus is symmetrically similar to the immune system in terms of internal network structure and external invasion threats. In this work, we use an intrusion detection method based on the dendritic cell algorithm (DCA). However, existing studies suggest the use of optimization methods to improve the accuracy of classification algorithms, and the current optimization of the parameters of the detection method mostly relies on the manual tuning of the parameters, which is a large workload. In view of the above challenges, this paper proposes a new detection algorithm based on the particle swarm optimization algorithm (PSO) and gravitational search algorithm (GSA) to improve the dendritic cell algorithm (PSO-GSA-DCA). PSO-GSA-DCA achieves adaptive parameter tuning and improves detection accuracy by mixing optimization algorithms and using them to optimize the dendritic cell algorithm classifier. Additionally, DCA-based CAN message attribute matching rules (measured by information gain and standard deviation of CAN data) are proposed for matching the three input signals (PAMP, DS, SS) of the DCA. The experimental results show that our proposed scheme has a significant improvement in accuracy, which can reach 91.64%, and lower time loss compared with other correlation anomaly detection schemes. Our proposed method also enables adaptive tuning, which solves the problem that most models now rely on manual tuning.

Lightweight IDS Framework Using Word Embeddings for In-Vehicle Network Security

As modern vehicle systems evolve into advanced cyber-physical systems, vehicle vulnerability to cyber threats has significantly increased. This paper discusses the need for advanced security in the Controller Area Network (CAN), which currently lacks security features. We propose a novel Intrusion Detection System (IDS) utilizing word embedding techniques from Natural Language Processing (NLP) for effective sequential pattern representations to improve intrusion detection in CAN traffic. This method transforms CAN identifiers into multi-dimensional vectors, enabling the model to capture complex sequential patterns of CAN traffic behaviors. Our methodology focuses on a lightweight neural network adaptable for automotive systems with limited computational resources. At first, a Word2Vec model is trained to make the embedding matrix of CAN IDs. Then, using the pre-trained embedding layer extracted from the Word2Vec network, the classifier analyzes embeddings from CAN data to detect intrusions. This model is viable for resource-constrained environments due to its low computational expense and memory usage. Key contributions of this research are (1) the application of word embeddings for intrusion detection in CAN traffic, (2) a streamlined neural network that balances accuracy with efficiency, and (3) a comprehensive evaluation showing our model’s competitive performance compared to relatively heavy deep learning models. Experimental results using the Car-Hacking dataset, widely used for automotive security research, demonstrate that our IDS effectively detects four different types of attacks on CAN. This work advances vehicle security technologies, contributing to safer transportation systems.

Vehicular Multilevel Data Arrangement-Based Intrusion Detection System for In-Vehicle CAN

Modern vehicles are equipped with various types of electrical/electronic (E/E) systems. Electronic control units (ECUs) are used to control various E/E systems in the vehicle. For efficient information exchange between ECUs, most vehicle manufacturers use the Controller Area Network (CAN) protocol. However, CAN has security vulnerabilities because it does not have an authentication or encryption method. Since attacks on in-vehicle networks affect the safety of drivers, it is essential to develop a technology to prevent attacks. The intrusion detection system (IDS) is one of the best ways to enhance network security. Unlike the traditional IDS for network security, IDS for the in-vehicle network requires a lightweight algorithm because of the limitation of the computing power of in-vehicle ECUs. In this paper, we propose a lightweight IDS algorithm for in-vehicle CAN based on the degree of change between successive data frames. In particular, the proposed method minimizes the load on the ECU by using the CAN data frame compression algorithm based on exclusive-OR operations as a tool for calculating the degree of change.

SDAE+Bi-LSTM-Based Situation Awareness Algorithm for the CAN Bus of Intelligent Connected Vehicles

With a deep connection to the internet, the controller area network (CAN) bus of intelligent connected vehicles (ICVs) has suffered many network attacks. A deep situation awareness method is urgently needed to judge whether network attacks will occur in the future. However, traditional shallow methods cannot extract deep features from CAN data with noise to accurately detect attacks. To solve these problems, we developed a SDAE+Bi-LSTM based situation awareness algorithm for the CAN bus of ICVs, simply called SDBL. Firstly, the stacked denoising auto-encoder (SDAE) model was used to compress the CAN data with noise and extract the deep spatial features at a certain time, to reduce the impact of noise. Secondly, a bidirectional long short-term memory (Bi-LSTM) model was further built to capture the periodic features from two directions to enhance the accuracy of the future situation prediction. Finally, a threat assessment model was constructed to evaluate the risk level of the CAN bus. Extensive experiments also verified the improved performance of our SDBL algorithm.

Anomaly Detection for In-Vehicle Network Using CNN-LSTM With Attention Mechanism

With the increasing connectivity between the Electronic Control Units (ECUs) and the outside world, safety and security have become stringent problems. The Controller Area Network (CAN) bus is the most commonly used in-vehicle network protocol, which lacks security mechanisms by design, so it is vulnerable to various attacks. In this paper, we propose a novel intrusion detection model called CNN-LSTM with Attention model (CLAM) for the in-vehicle network, especially CAN. The CLAM model uses one-dimensional convolution (Conv1D) to extract the abstract features of the signal values at each time step and feeds it into the Bidirectional Long Short Term Memory (Bi-LSTM) to extract the time dependence. By combining the attention mechanisms, we calculate the weight of each hidden state output by Bi-LSTM and perform a weighted summation, so that the model focuses only on locally important time steps, which can improve the convergence speed of the model and prediction accuracy. The proposed model uses the bit flip rate to extract continuous signal boundaries in the 64-bit CAN data, so it does not need to parse the CAN communication matrix and is suitable for different vehicles. The extensive evaluation results demonstrate that our proposed CLAM model can effectively detect CAN attacks, with an average F1-score of 0.951 and an error rate of 2.16%. Compared with the work in related research fields, the accuracy of attack detection is improved by 2.5%.

Advanced optical methods for safe image reproduction on automotive displays

AbstractModern cars are equipped with camera monitor systems (CMSs), such as a backup camera or side‐mirror replacement. These systems are expected to perform optimally and achieve high safety levels (ASIL). Currently, only digital data are supervised in CMSs and safety mechanisms for such systems are individually derived on a case‐by‐case basis which is not effective. This study proposes generic optical supervision for displays of automotive CMS. This paper introduces “light‐to‐light” (camera to display output) protection for both in‐car CMS and remote operator monitors used in autonomous car fleet operation centers. The first method is based on photodiodes attached to the display to optically supervise, for instance, the speedometer of vehicles. By combining intensities of photodiodes with calibration data, we can compare the measured speed with the value from CAN (Controller Area Network) data. The second method that entails capturing the display content using a camera enables top safety levels for both in‐car displays and remote operator monitors. This safeguarding was successfully verified by conventional image processing and artificial intelligence (AI)‐based analysis methods. Our results demonstrate that AI methods allow a substantial reduction in the wireless transmission bandwidth from a car to a remote operator compared with conventional image processing.

An Enhanced Method for Reverse Engineering CAN Data Payload

Recently, numerous electronic components are installed in vehicles, providing drivers and passengers with increased safety and convenience. The electronic components construct an in-vehicle network that internally shares relevant status information about the vehicle. As modern vehicles become more computerized, the potential for automotive cyber-security threats also increases a fact that has been illustrated clearly by various car-hacking demonstrations. Using the controller area network (CAN), the de facto standard protocol in the automotive industry that facilitates in-vehicle network communication, car-hacking demonstrations inject critical CAN messages to control vehicular functions. In efforts to address this security issue, car manufacturers, in turn, have made confidential the CAN database (i.e., DBC format file), where signal information assigned in the CAN data payload is specified. However, it has since become known that this policy does not hermetically seal a vehicular network against cyber attacks. On the contrary, in-depth automotive security research has been hindered significantly because of the limited information accessible by researchers. For example, automotive intrusion detection systems (IDS) identify and alert when there is a vehicular break-in, and this technology is a major area of study in automotive cyber security research. For the automotive IDS that analyzes CAN traffic, information in the DBC format file greatly improves detection veracity. However, most IDS technologies to date have been independently developed without the confidential CAN DB information and, as a result, do not mitigate threats to a satisfactory standard. In this paper, we propose an enhanced method that identifies signal boundaries in a CAN data payload, which is specified in the DBC format file. Unlike an existing method that is designed based on total bit-flip rates, our method analyzes bit-flip time series not total bit-flip rates so that signal boundaries can be more clearly identified. In this paper, we use a publicly available DBC format file called OpenDBC as a reference, and show that our method outperforms the existing method.

Covert Channel-Based Transmitter Authentication in Controller Area Networks

In recent years, the security of automotive Cyber-Physical Systems (CPSs) is facing urgent threats due to the widespread use of legacy in-vehicle communication systems. As a representative legacy bus system, the Controller Area Network (CAN) hosts Electronic Control Units (ECUs) that are crucial for the vehicles functioning. In this scenario, malicious actors can exploit the CAN vulnerabilities, such as the lack of built-in authentication and encryption schemes, to launch CAN bus attacks (e.g., suspension, injection, and masquerade attacks) with life-threatening consequences (e.g., disabling brakes). In this article, we present TACAN (Transmitter Authentication in CAN), which provides secure authentication of ECUs on the legacy CAN bus by exploiting the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">covert channels</i> , without introducing CAN protocol modifications or traffic overheads (no extra bits or CAN messages are used). TACAN turns upside-down the originally malicious concept of covert channels and exploits it to build an effective defensive technique that facilitates transmitter authentication via a centralized, trusted Monitor Node. TACAN consists of three different covert channels for ECU authentication: 1) the Inter-Arrival Time (IAT)-based, leveraging the IATs of CAN messages; 2) the Least Significant Bit (LSB)-based, concealing authentication messages into the LSBs of normal CAN data; and 3) a hybrid covert channel, exploiting the combination of the first two. In order to validate TACAN, we implement the covert channels on the University of Washington (UW) EcoCAR (Chevrolet Camaro 2016) testbed. We further evaluate the bit error, throughput, and detection performance of TACAN through extensive experiments using the EcoCAR testbed and a publicly available dataset collected from Toyota Camry 2010. We demonstrate the feasibility of TACAN and the effectiveness of detecting CAN bus attacks, highlighting no traffic overheads and attesting the regular functionality of ECUs.

Predicting the sugarcane yield in real-time by harvester engine parameters and machine learning approaches

Information regarding sugarcane yield is the starting point for the application of Precision Agriculture (PA) strategies to the management of sugarcane fields. Over the years, many sugarcane yield monitoring approaches have been developed and tested, but its use is still limited. One option is to use data generated by the sugarcane harvester provided in the controller area network (CAN), which allows getting the messages related to the harvester operation. Our goal was to train and to test random forest (RF), multiple linear regression (MLR), and artificial neural network (ANN) using CAN data available on the on-board computer of the harvester. All predictive models were trained and tested using the main engine parameters: fuel consumption, engine rotation, engine power, and specific fuel consumption (SFC) as data input. A scale yield monitor was installed on the harvester elevator to provide the georeferenced yield data. The yield prediction accuracy of the predictive models using the four parameters was compared. All models followed the observed sugarcane yield and recognized the changes over the time of data collection. The MLR and ANN models have a higher error of prediction in the extreme values of yield. Over the testing time, the ANN underestimated the sugarcane yield, and the RF prediction by the engine parameters of the harvester was coming closest to the observed yield. The best results for predicting sugarcane yield by engine parameters were obtained from the RF model with a mean absolute percent error (MAPE) of 5.6%, and root mean square error (RMSE) of 7.0 Mg ha−1. The MLR and ANN models have a MAPE of 7.8% and 5.6%, respectively. All the variables were necessary for a better performance of the models; however, SFC was the most important variable for predicting sugarcane yield.