Analysis of Security Vulnerability Levels of In-Vehicle Network Topologies Applying Graph Representations

This article investigates cybersecurity issues related to in-vehicle communication networks. In-vehicle communication network security is evaluated based on the protection characteristics of the network components and the topology of the network. The automotive communication network topologies are represented as undirected weighted graphs, and their vulnerability is estimated based on the specific characteristics of the generated graph. Thirteen different vehicle models have been investigated to compare the vulnerability levels of the in-vehicle network using the Dijkstra's shortest route algorithm. An important advantage of the proposed method is that it is in accordance with the most relevant security evaluation models. On the other hand, the newly introduced approach considers the Secure-by-Design concept principles.

Attacks to Automatous Vehicles: A Deep Learning Algorithm for Cybersecurity

Rapid technological development has changed drastically the automotive industry. Network communication has improved, helping the vehicles transition from completely machine- to software-controlled technologies. The autonomous vehicle network is controlled by the controller area network (CAN) bus protocol. Nevertheless, the autonomous vehicle network still has issues and weaknesses concerning cybersecurity due to the complexity of data and traffic behaviors that benefit the unauthorized intrusion to a CAN bus and several types of attacks. Therefore, developing systems to rapidly detect message attacks in CAN is one of the biggest challenges. This study presents a high-performance system with an artificial intelligence approach that protects the vehicle network from cyber threats. The system secures the autonomous vehicle from intrusions by using deep learning approaches. The proposed security system was verified by using a real automatic vehicle network dataset, including spoofing, flood, replaying attacks, and benign packets. Preprocessing was applied to convert the categorical data into numerical. This dataset was processed by using the convolution neural network (CNN) and a hybrid network combining CNN and long short-term memory (CNN-LSTM) models to identify attack messages. The results revealed that the model achieved high performance, as evaluated by the metrics of precision, recall, F1 score, and accuracy. The proposed system achieved high accuracy (97.30%). Along with the empirical demonstration, the proposed system enhanced the detection and classification accuracy compared with the existing systems and was proven to have superior performance for real-time CAN bus security.

A Vehicle Can Bus Anomaly Detection Method for Periodic Attacks Based on the Entropy Model

Because of the rapid development of automobile intelligence and networking, cyber attackers can invade the vehicle network via wired and wireless interfaces, such as physical interfaces, short-range wireless interfaces, and long-range wireless interfaces. Thus, interfering with regular driving will immediately jeopardises the drivers’ and passengers’ personal and property safety. To accomplish security protection for the vehicle CAN (Controller Area Network) bus, we propose an anomaly detection method by calculating the information entropy based on the number of interval messages during the sliding window. It detects periodic attacks on the vehicle CAN bus, such as replay attacks and flooding attacks. First, we calculate the number of interval messages according to the CAN bus baud rate, the number of bits of a single frame message, and the time required to calculate information entropy within the window. Second, we compute the window information entropy of regular packet interval packets and determine the normal threshold range by setting a threshold coefficient. Finally, we calculate the information entropy of the data to be measured, determine whether it is greater than or less than the threshold, and detect the anomaly. The experiment uses CANoe software to simulate the vehicle network. It uses the body frame CAN bus network of a brand automobile body bench as the regular network, simulates attack nodes to attack the regular network periodically, collects message data, and verifies the proposed detection method. The results show that the proposed detection method has lower false-negative and false-positive rates for attack scenarios such as replay attacks and flood attacks across different attack cycles.

A Review on Forwarding Strategies in NDN based Vehicular Networks

Named Data Networking (NDN) is a model that has been proposed by many researchers to alter the long-established IP based networking model. It derives the content centric approach rather than host-based approach. This is gaining even more traction in the wireless network and is able to replace the conventional IP-based networking. Up to now, NDN has proven to be fruitful when used with certain limitations in vehicular networks. Vehicular networks deal with exchanging information across fast moving complex vehicle network topology. The sending and receiving of information in such a scenario acts as a challenge and thus requires an effective forwarding strategy to address this problem. Different research work has provided with multiple forwarding strategy that solves the current problem up to some limit but further research work is still longed for to get an optimum solution. This paper provides a brief survey on current existing forwarding strategies related to vehicular networks using NDN as well as providing information on various resources and technologies used in it.

Beacon-Based Hybrid Routing Protocol for Large-Scale Unmanned Vehicle Ad Hoc Network

In this paper, we designed a beacon-based hybrid routing protocol to adapt to the new forms of intelligent warfare, accelerate the application of unmanned vehicles in the military field, and solve the problems such as high maintenance cost, path failure, and repeated routing pathfinding in large-scale unmanned vehicle network communications for new battlefields. This protocol used the periodic broadcast pulses initiated by the beacon nodes to provide synchronization and routing to the network and established a spanning tree through which the nodes communicated with each other. An NS3 platform was used to build a dynamic simulation environment of service data to evaluate the network performance. The results showed that when it was used in a range of 5 ~ 35 communication links, the beacon-based routing protocol’s PDR was approximately 10% higher than that of AODV routing protocol. At 5 ~ 50 communication links, the result was approximately 20% higher than the DSDV routing protocol. The routing load was not related to the number of nodes and communication link data and the protocol had better performance than traditional AODV and DSDV routing protocol, which reduced the cost of the routing protocol and effectively improved the stability and reliability of the network. The protocol we designed is more suitable for the scenarios of large-scale unmanned vehicle network communication in the future AI battlefield.

ANOMALY-BASED INTRUSION DETECTION FOR A VEHICLE CAN BUS: A CASE FOR HYUNDAI AVANTE CN7

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.