In-vehicle Security Research Articles

HybridSecNet: In-Vehicle Security on Controller Area Networks Through a Hybrid Two-Step LSTM-CNN Model

HybridSecNet: In-Vehicle Security on Controller Area Networks Through a Hybrid Two-Step LSTM-CNN Model

Efficient Secure Mechanisms for In-Vehicle Ethernet in Autonomous Vehicles

The integration of external devices and network connectivity into autonomous vehicles has raised significant concerns about in-vehicle security vulnerabilities. Existing security mechanisms for in-vehicle bus systems, which mainly rely on appending authentication codes and data encryption, have been extensively studied in the context of CAN and CAN-FD buses. However, these approaches are not directly applicable to Ethernet buses due to the much higher data transmission rates of Ethernet buses compared to other buses. The real-time encryption and decryption required by Ethernet buses cannot be achieved with conventional methods, necessitating an acceleration in the speed of cryptographic operations to match the demands of Ethernet communication. In response to these challenges, our paper introduces a range of cryptographic solutions specifically designed for in-vehicle Ethernet networks. We employ an AES-ECC hybrid algorithm for critical vehicle control signals, combining the efficiency of AES with the security of ECC. For multimedia signals, we propose an improved AES-128 (IAES-128) and an improved MD5 (IMD), which improve encryption time by 15.77%. Our proposed security mechanisms have been rigorously tested through attack simulations on the CANoe (version 10) platform. These tests cover both in-vehicle control signals, such as braking and throttle control, and non-critical systems like multimedia entertainment. The experimental results convincingly demonstrate that our optimized algorithms and security mechanisms ensure the secure and reliable operation of real-time communication in autonomous vehicles.

A robust multi-stage intrusion detection system for in-vehicle network security using hierarchical federated learning

As connected and autonomous vehicles proliferate, the Controller Area Network (CAN) bus has become the predominant communication standard for in-vehicle networks due to its speed and efficiency. However, the CAN bus lacks basic security measures such as authentication and encryption, making it highly vulnerable to cyberattacks. To ensure in-vehicle security, intrusion detection systems (IDSs) must detect seen attacks and provide a robust defense against new, unseen attacks while remaining lightweight for practical deployment. Previous work has relied solely on the CAN ID feature or has used traditional machine learning (ML) approaches with manual feature extraction. These approaches overlook other exploitable features, making it challenging to adapt to new unseen attack variants and compromising security. This paper introduces a cutting-edge, novel, lightweight, in-vehicle, IDS-leveraging, deep learning (DL) algorithm to address these limitations. The proposed IDS employs a multi-stage approach: an artificial neural network (ANN) in the first stage to detect seen attacks, and a Long Short-Term Memory (LSTM) autoencoder in the second stage to detect new, unseen attacks. To understand and analyze diverse driving behaviors, update the model with the latest attack patterns, and preserve data privacy, we propose a theoretical framework to deploy our IDS in a hierarchical federated learning (H-FL) environment. Experimental results demonstrate that our IDS achieves an F1-score exceeding 0.99 for seen attacks and exceeding 0.95 for novel attacks, with a detection rate of 99.99%. Additionally, the false alarm rate (FAR) is exceptionally low at 0.016%, minimizing false alarms. Despite using DL algorithms known for their effectiveness in identifying sophisticated and zero-day attacks, the IDS remains lightweight, ensuring its feasibility for real-world deployment. This makes our model robust against seen and unseen attacks.

Implementation and Evaluation of Lightweight in-Vehicle Security Switch with Hierarchical Hash Table

Implementation and Evaluation of Lightweight in-Vehicle Security Switch with Hierarchical Hash Table

A novel and efficient framework for in-vehicle security enforcement

The Internet of Vehicles (IoV) has garnered significant popularity thanks to rapid technological advancements and the widespread availability of the Internet. IoV encompasses vehicles with multiple electronic control units (ECUs) interconnected via advanced intra-vehicle networks. These networks play a crucial role in managing various vehicle functions, with the Controller Area Network (CAN) being of particular significance. However, the increased adoption of intelligent vehicles has also led to a rise in cyberattacks in the intra-vehicular network. These existing vulnerabilities pose significant security and user safety challenges. Extensive efforts have been dedicated to enhancing intra-vehicular network security. Yet, there are open concerns with limited progress made by academic and industry experts on effectively detecting CAN bus attacks. These concerns are essential to ensure intelligent vehicles’ overall security and safety. It requires collaboration between academia, industry, and the development of innovative solutions to fortify vehicular networks against evolving cyber threats. Current intra-vehicular security systems need more robustness and need to consider intelligent methodologies in their proposed works. To overcome all these limitations, This paper introduces a novel intrusion detection framework for in-vehicle networks based on integrating federated learning with transfer learning, improving the detection capabilities of individual vehicles within the network. Our framework employs a trusted authority for secure communication, a cloud server for model distribution and aggregation, and leverages the CAN bus for data collection and training. It guarantees that vehicles start with standardized baseline models and refine them through transfer learning, resulting in a collective intelligence-based final IDS engine for ongoing improvement. We used the Maximum Mean Discrepancy (MMD) to select data from the source domain similar to the target domain. The selected data is more likely to contain patterns and features useful for detecting intrusions in the target domain, leading to better generalization and detection capabilities.

In-Vehicle Network Intrusion Detection System Using Convolutional Neural Network and Multi-Scale Histograms

Cybersecurity in modern vehicles has received increased attention from the research community in recent years. Intrusion Detection Systems (IDSs) are one of the techniques used to detect and mitigate cybersecurity risks. This paper proposes a novel implementation of an IDS for in-vehicle security networks based on the concept of multi-scale histograms, which capture the frequencies of message identifiers in CAN-bus in-vehicle networks. In comparison to existing approaches in the literature based on a single histogram, the proposed approach widens the informative context used by the IDS for traffic analysis by taking into consideration sequences of two and three CAN-bus messages to create multi-scale dictionaries. The histograms are created from windows of in-vehicle network traffic. A preliminary multi-scale histogram model is created using only legitimate traffic. Against this model, the IDS performs traffic analysis to create a feature space based on the correlation of the histograms. Then, the created feature space is given in input to a Convolutional Neural Network (CNN) for the identification of the windows of traffic where the attack is present. The proposed approach has been evaluated on two different public data sets achieving a very competitive performance in comparison to the literature.

Self-Aware Cybersecurity Architecture for Autonomous Vehicles: Security through System-Level Accountability.

The inherent dynamism of recent technological advancements in intelligent vehicles has seen multitudes of noteworthy security concerns regarding interactions and data. As future mobility embraces the concept of vehicles-to-everything, it exacerbates security complexities and challenges concerning dynamism, adaptiveness, and self-awareness. It calls for a transition from security measures relying on static approaches and implementations. Therefore, to address this transition, this work proposes a hierarchical self-aware security architecture that effectively establishes accountability at the system level and further illustrates why such a proposed security architecture is relevant to intelligent vehicles. The article provides (1) a comprehensive understanding of the self-aware security concept, with emphasis on its hierarchical security architecture that enables system-level accountability, and (2) a deep dive into each layer supported by algorithms and a security-specific in-vehicle black box with external virtual security operation center (VSOC) interactions. In contrast to the present in-vehicle security measures, this architecture introduces characteristics and properties that enact self-awareness through system-level accountability. It implements hierarchical layers that enable real-time monitoring, analysis, decision-making, and in-vehicle and remote site integration regarding security-related decisions and activities.

User expectations and perceptions towards new public transport infrastructure: evaluating a cable car in Bogotá

Cable cars are a viable alternative to improve citizens’ accessibility in zones with limitations on urban public transport supply due to the topography. In Latin America, such systems have recently been implemented in zones with high levels of poverty and vulnerability. Although the social implications of their implementation are relevant, individual expectations of these systems and how current changes in travel conditions and quality of life are perceived have not been widely reported in the literature. This paper aims to evaluate users’ expectations and perceptions of a new cable car in the southern periphery of Bogotá (Colombia). We conducted a panel survey before (n = 341) and after (n = 301) the cable car started operations to evaluate the ranking of preferences toward a set of possible benefits of the project. We estimated discrete choice models to analyze the statistical differences between the expectations and perceptions before and after changes. Results suggest that travel time reductions, comfort improvements, and in-vehicle security are the benefits most valued by the users. Even though the project meets expectations of these aspects, it seems to fall short in expectations of reductions of pollution. Individuals’ experience with the cable car shapes their perceptions of the system. We found that perceptions differ between those who have used the service at least once and those who never did. Policy implications derived from this study might be of interest to decision-makers seeking to guarantee the public acceptability of urban projects.

Context-Aware Security for Vehicles and Fleets: A Survey

Vehicles are becoming increasingly intelligent and connected. Interfaces for communication with the vehicle, such as WiFi and 5G, enable seamless integration into the user's life, but also cyber attacks on the vehicle. Therefore, research is working on in-vehicle countermeasures such as authentication, access controls, or intrusion detection. Recently, legal regulations have also become effective that require automobile manufacturers to set up a monitoring system for fleet-wide security analysis. The growing amount of software, networking, and the automation of driving create new challenges for security. Context-awareness, situational understanding, adaptive security, and threat intelligence are necessary to cope with these ever-increasing risks. In-vehicle security should be adaptive to secure the car in an infinite number of (driving) situations. For fleet-wide analysis and alert triage, knowledge and understanding of the circumstances are required. Context-awareness, nonetheless, has been sparsely considered in the field of vehicle security. This work aims to be a precursor to context-aware, adaptive and intelligent security for vehicles and fleets. To this end, we provide a comprehensive literature review that analyzes the vehicular as well as related domains. Our survey is mainly characterized by the detailed analysis of the context information that is relevant for vehicle security in the future.

DESOLATER: Deep Reinforcement Learning-Based Resource Allocation and Moving Target Defense Deployment Framework

The recent development of autonomous driving technologies has led to the proliferation of research on sensors and electronic equipment inside a vehicle. To deal with security concerns of in-vehicle networks, various deep learning (DL) and reinforcement learning (RL) have been developed to enhance in-vehicle security. However, the DL/RL agents are vulnerable to adversarial perturbation, where an attacker can perform a manipulation attack to interfere with the agent’s operation. In this work, we aim to develop two key mechanisms to build secure in-vehicle networks: (1) RL-based proactive defense mechanism to achieve multiple objectives of minimizing system security vulnerabilities while maximizing service availability; and (2) a resilient RL method that allows an agent to operate in the presence of adversarial disturbances that neutralize the system security. To this end, we propose, DESOLATER ( D rl-based r ESO urce a L location A nd m T d d E ployment f R amework), which is a multi-agent deep reinforcement learning (mDRL)-based network slicing technique that can help determine two key network management decisions: (1) link bandwidth allocation to meet quality-of-service (QoS) requirements; and (2) the frequency of triggering IP shuffling as a proactive defense mechanism not to hinder service availability by maintaining normal system operations. We also introduce an anomaly detection mechanism with a memory-based RL technique to enhance the resiliency of the RL agents in a partially observable environment under the situation that adversarial attackers manipulating observation information. Through extensive simulation experiments, we validate that the proposed robust mDRL algorithm can help the deployed proactive security mechanism achieve both security and network performance improvement in the presence of adversarial attacks.

Detecting In-Vehicle Attacks with Deep Learning: An Applied Approach

With the increasing number of connected vehicles on the road, the need for secure in-vehicle systems is more pressing than ever. In-vehicle attacks can compromise the safety and privacy of drivers and passengers, and the detection of such attacks is crucial to prevent potential harm. In this paper, we propose an applied deep learning approach for detecting in-vehicle attacks. Our approach is based on a gated recurrent unit (GRU) that is trained on a dataset of network traffic collected from in-vehicle communication systems. We evaluate our approach on a real-world dataset and demonstrate its effectiveness in detecting different types of in-vehicle attacks, including denial of service (DoS), remote replay attacks, and flooding attacks. Our results show that the proposed approach can achieve high accuracy in detecting in-vehicle attacks. We also compare our approach with traditional machine learning algorithms and show that our approach outperforms them in terms of accuracy. Our proposed approach can be used as a standalone system or as a complementary solution to existing in-vehicle security systems to enhance the overall cybersecurity of connected vehicles.

Intrusion detection system using deep learning for in-vehicle security

With the development of vehicle intelligence technology, the combination of network and vehicle becomes inevitable, which brings much convenience to people. At the same time, hackers can also use technical vulnerabilities to attack vehicles, leading to severe traffic accidents and even vehicle crash. Based on this situation, the vehicle information security protection techniques have drawn great attention from researchers. This paper studies the vehicle intrusion detection system (IDS) based on the neural network algorithm in deep learning, and uses gradient descent with momentum (GDM) and gradient descent with momentum and adaptive gain (GDM/AG) to improve the efficiency and accuracy of IDS. The accuracy and efficiency of the proposed model are validated and evaluated by using real vehicles at the end of the paper. Experiments show that the GDM/AG algorithm can achieve faster convergence in comparison with the GDM algorithm in vehicle anomaly detection, and can detect anomaly data at the level of milliseconds. At the same time, the proposed model can adapt itself to detect unknown attacks. The veracity rate ranges from 97% to 98% in directing the adaptation when facing unknown attack types.

Dynamic Scalable Elliptic Curve Cryptographic Scheme and Its Application to In-Vehicle Security

The design of unified, efficient, and lightweight cryptographic platform for resource-constrained on-board devices such as sensors, microcontrollers, and actuators in the context of Internet of Vehicles remains an open and challenging problem, for both academic and industry. Elliptic curve cryptography (ECC) is considered as a promising encryption algorithm for the next generation communications, as it could provide the same strong security level using relatively smaller key size when compared to the currently used Rivest–Shamir–Adleman algorithm. However, traditional ECCs have the disadvantage of using a fixed curve, making it very easy to be intensively analyzed while being hard to construct a united platform for on-board devices with processors of different instruction lengths. To mitigate the above problem, this paper suggests a dynamic scalable elliptic curve cryptosystem. To synchronize the curve in use, a curve list of different security levels is generated and preserved on both parties. Since both parties randomly choose the curve and the prime number, a extra security level could be provided, so that the security level can still remain the same even using smaller key sizes, while the computation efficiency will be enhanced and the power consumption will be reduced, which is especially suitable for the application in on-board embedded devices. Detailed experimental results illustrate that the presented scheme improves the efficiency by 30% in average when compared with traditional ECC implementations on a similar security level. Therefore, the proposed scalable ECC scheme as a unified cryptographic platform is more economic for these on-board devices in vehicles.

NOTSA: Novel OBU With Three-Level Security Architecture for Internet of Vehicles

Internet of Vehicles has become a massive network, which enables multinetwork fusion, including in-vehicle network, wireless local area network, dedicated short range communication, device-to-device communication, and cellular network (e.g., 5G). Proverbially, in-vehicle network is considered as a closed network and thus absolutely secure. However, multiple networks access and fusion can introduce different threats. Current on board units (OBUs) fail to protect in-vehicle network. Therefore, illegal vehicle control can be easily performed for attackers. In this paper, in consideration of vulnerabilities of current OBUs and in-vehicle controller area network, we show main attack model for actual vehicles, and assess introduced threats using the approach based on ISO 13335 guidelines for the management of IT security. Then, we design the novel OBU with three-level security architecture (NOTSA) and propose multilevel security protocols. It cannot only improve the security of external networks, but also protect the in-vehicle network by collaborating with current in-vehicle security schemes. Thereafter, we analyze security of proposed scheme, and evaluate it on hardware platform. The reliability of NOTSA and vehicular ad-hoc networks are then discussed using reliability block diagrams. In addition, we also verify the correctness of proposed protocols. Finally, the simulation results and comparison show that our scheme is feasible and more efficient than existing schemes in term of time overhead, security and reliability.

Intrusion detection system using SOEKS and deep learning for in-vehicle security

With the continuous development of the intelligent vehicle, vehicle security events occur frequently, therefore, the vehicle information security is particularly important. In this paper, the in-vehicle security measures are analyzed, especially the current situation of in-vehicle intrusion detection system, which are mainly aimed at specific vehicles and are not enough to meet the need of vehicle security. Then, a new in-vehicle intrusion detection mechanism is proposed based on deep learning and the set of experience knowledge structure (SOEKS), which is a knowledge representation structure. Utilizing SOEKS and information entropy to increase the versatility of intrusion detection for different vehicle. In practice, the more precise model for specific vehicle can formed by training a large amount of specific vehicle data through deep learning. It is demonstrated with experimental results that the proposed approach is able to have 98% accuracy and detect a wide range of in-vehicle attacks.

A survey on the cryptographic approaches for CAN bus automotive networks

Electronic control units, so called ECUs are a major part in a today car's architecture. These devises are dedicated to control and monitor different functions in-vehicle. So, a secure communication, between those ECUs, is required. Modern cars can contain from 70-100 of ECUs which are interconnected via several protocols to form an overall internal network controller area network (CAN) bus has become the widely used among these protocol. However, CAN bus does not have enough security prosperities to protect the whole automotive system even to protect its network. Furthermore, today's car is characterised with an important external connectivity through several devices such as of Wi-Fi, Bluetooth and USB. Unfortunately, the increase of connectivity and complexity of modern in-automotive networks have increased the possibility of attacks against vehicle. So, to leave in-vehicle security level, some defence mechanisms, such as cryptographic and intrusion detection systems, are proposed. In this paper, we present, on one hand, a survey on current restrictions of CAN bus to insure a secure communication. On second hand, we give some approaches to solve CAN bus security.

Passenger's subjective traffic safety, in-vehicle security and emergency management in the driverless shuttle bus in Finland

Mobility services are evolving globally. Driverless public transport can be a game-changer for urban mobility. However, empirical evidence from the point of user experiences is lacking. A customer's sense of safety and security has a significant influence on public transport acceptance. This case study focuses on driverless shuttle bus passengers' subjective experiences of (a) traffic safety, (b) in-vehicle security, and (c) emergency management compared to the conventional bus. Data were collected through interviews from informants that travelled by driverless shuttle busses in the City of Vantaa, Finland in summer 2015. A total of 19,021 passengers travelled by 3,962 km autonomous buses on a specific route. The sample of 197 informants was analysed by quantitative methods. Informants assessed perception of traffic safety to be better in the driverless shuttle bus than in a conventional bus with a driver. However, they were lacking personal in-vehicle security. 64 per cent of passengers answered that sense of in-vehicle security in the driverless shuttle bus was worse or much worse than in the conventional bus. There was a significant difference between women and men when they evaluated their subjective sense of security on board F(1, 195) = 8.196, p < 0.001. Men assessed their experiences of traffic safety, in-vehicle security and emergency management to be overall better than those of women. In order to mainstream the use of driverless shuttle buses, for example as a part of a transport chain, traffic safety is not a problem. Instead, a passenger's sense of security on board should be increased. This is the case especially with female passengers.

Analysis on in-vehicle information security defense

With the continuous infiltration of in-vehicle smart devices, the once-closed in-vehicle network has become an open- ing environment and the problem of in-vehicle information security becomes increasingly prominent day by day. In this paper, we analyzed the harm of in-vehicle information security problem on basis of which we further conducted study on correspond- ing defense demands and summarized the suitable method of analysis; directed against the demand for in-vehicle information security, we conducted analysis on in-vehicle information security defense and summarized the information defending strate- gies of in-vehicle network and in-vehicle field bus; we studied the technologies used in the in-vehicle information security encryption mechanism and made comparative analysis towards the main algorithm.

Investigation into In-Vehicle Information Security

Along with the penetration of in-vehicle intelligent devices, the in-vehicle networks are changed from a closed environment to an open environment, and thus the concern of in-vehicle information security becomes increasingly prominent. In this paper, we analyzed the damages of in-vehicle information insecurity, studied the corresponding defense requirements, and summarized the applicable analytical methods. Based on the demands for in-vehicle information security, we analyzed the corresponding defenses, and summarized the defense approaches for in-vehicle networks and in-vehicle field-bus information security.