Biblio

Steady advancement in Artificial Intelligence (AI) development over recent years has caused AI systems to become more readily adopted across industry and military use-cases globally. As powerful as these algorithms are, there are still gaping questions regarding their security and reliability. Beyond adversarial machine learning, software supply chain vulnerabilities and model backdoor injection exploits are emerging as potential threats to the physical safety of AI reliant CPS such as autonomous vehicles. In this work in progress paper, we introduce the concept of AI supply chain vulnerabilities with a provided proof of concept autonomous exploitation framework. We investigate the viability of algorithm backdoors and software third party library dependencies for applicability into modern AI attack kill chains. We leverage an autonomous vehicle case study for demonstrating the applicability of our offensive methodologies within a realistic AI CPS operating environment.

The emergence of smart cars has revolutionized the automotive industry. Today's vehicles are equipped with different types of electronic control units (ECUs) that enable autonomous functionalities like self-driving, self-parking, lane keeping, and collision avoidance. The ECUs are connected to each other through an in-vehicle network, named Controller Area Network. In this talk, we will present the different cyber attacks that target autonomous vehicles and explain how an intrusion detection system (IDS) using machine learning can play a role in securing the Controller Area Network. We will also discuss the main research contributions for the security of autonomous vehicles. Specifically, we will describe our IDS, named Histogram-based Intrusion Detection and Filtering framework. Next, we will talk about the machine learning explainability issue that limits the acceptability of machine learning in autonomous vehicles, and how it can be addressed using our novel intrusion detection system based on rule extraction methods from Deep Neural Networks.

Connected Autonomous Vehicle (CAV) applications have shown the promise of transformative impact on road safety, transportation experience, and sustainability. However, they open large and complex attack surfaces: an adversary can corrupt sensory and communication inputs with catastrophic results. A key challenge in development of security solutions for CAV applications is the lack of effective infrastructure for evaluating such solutions. In this paper, we address the problem by designing an automated, flexible evaluation infrastructure for CAV security solutions. Our tool, CAVELIER, provides an extensible evaluation architecture for CAV security solutions against compromised communication and sensor channels. The tool can be customized for a variety of CAV applications and to target diverse usage models. We illustrate the framework with a number of case studies for security resiliency evaluation in Cooperative Adaptive Cruise Control (CACC).

One of the typical autonomous driving systems is a human-machine cooperative system that intervenes in the driver operation. The autonomous driving needs to make consideration of the driver individuality in addition to safety. This paper considers a human-machine cooperative system balancing safety with the driver individuality using the Human-In-The-Loop System (HITLS) for rear-wheel steering control. This paper assumes that it is safe for HITLS to follow the target side-slip angle and target angular velocity without conflicts between the controller and driver operations. We propose HITLS using the primal-dual algorithm and the internal model control (IMC) type I-PD controller. In HITLS, the signal expander delimits the human-selectable operating range and the controller cooperates stably the human operation and automated control in that range. The primal-dual algorithm realizes the driver and the signal expander. Our outcomes are the making of the rear-wheel steering system which converges to the target value while reflecting the driver individuality.

Autonomous vehicles (AVs) offer a wide range of promising benefits by reducing traffic accidents, environmental pollution, traffic congestion and land usage etc. However, to reap the intended benefits of AVs, it is inevitable that this technology should be trusted and accepted by the public. The consumer's substantial trust upon AVs will lead to its widespread adoption in the real-life. It is well understood that the preservation of strong security and privacy features influence a consumer's trust on a product in a positive manner. In this paper, we introduce a novel concept of digital labels for AVs to increase consumers awareness and trust regarding the security level of their vehicle. We present an architecture called Cybersecurity Box (CSBox) that leverages digital labels to display and inform consumers and passengers about cybersecurity status of the AV in use. The introduction of cybersecurity digital labels on the dashboard of AVs would attempt to increase the trust level of consumers and passengers on this promising technology.

Enabled by the industrial Internet, intelligent transportation has made remarkable achievements such as autonomous vehicles by carnegie mellon university (CMU) Navlab, Google Cars, Tesla, etc. Autonomous vehicles benefit, in various aspects, from the cooperation of the industrial Internet and cyber-physical systems. In this process, users in autonomous vehicles submit query contents, such as service interests or user locations, to service providers. However, privacy concerns arise since the query contents are exposed when the users are enjoying the services queried. Existing works on privacy preservation of query contents rely on location perturbation or k-anonymity, and they suffer from insufficient protection of privacy or low query utility incurred by processing multiple queries for a single query content. To achieve sufficient privacy preservation and satisfactory query utility for autonomous vehicles querying services in cyber-physical systems, this article proposes a novel privacy notion of client-based personalized k-anonymity (CPkA). To measure the performance of CPkA, we present a privacy metric and a utility metric, based on which, we formulate two problems to achieve the optimal CPkA in term of privacy and utility. An approach, including two modules, to establish mechanisms which achieve the optimal CPkA is presented. The first module is to build in-group mechanisms for achieving the optimal privacy within each content group. The second module includes linear programming-based methods to compute the optimal grouping strategies. The in-group mechanisms and the grouping strategies are combined to establish optimal CPkA mechanisms, which achieve the optimal privacy or the optimal utility. We employ real-life datasets and synthetic prior distributions to evaluate the CPkA mechanisms established by our approach. The evaluation results illustrate the effectiveness and efficiency of the established mechanisms.

Advances in artificial intelligence, machine learning, and robotics have profoundly impacted the field of autonomous navigation and driving. However, sensor spoofing attacks can compromise critical components and the control mechanisms of mobile robots. Therefore, understanding vulnerabilities in autonomous driving and developing countermeasures remains imperative for the safety of unmanned vehicles. Hence, we demonstrate cross-validation techniques for detecting spoofing attacks on the sensor data in autonomous driving in this work. First, we discuss how visual and inertial odometry (VIO) algorithms can provide a root-of-trust during navigation. Then, we develop examples for sensor data spoofing attacks using the open-source driving dataset. Next, we design an attack detection technique using VIO algorithms that cross-validates the navigation parameters using the IMU and the visual data. Following, we consider hardware-dependent attack survival mechanisms that support an autonomous system during an attack. Finally, we also provide an example of spoofing survival technique using on-board hardware oscillators. Our work demonstrates the applicability of classical mobile robotics algorithms and hardware security primitives in defending autonomous vehicles from targeted cyber attacks.

Increasingly, the transportation industry has moved towards automation to improve safety, fuel efficiency, and system productivity. However, the increased scrutiny that automated vehicles (AV) face over functional safety has hindered the industry's unbridled confidence in self-driving technologies. As AVs are cyber-physical systems, they utilize distributed control to accomplish a range of safety-critical driving tasks. The Operation Systems (OS) serve as the core of these control systems. Therefore, their designs and implementation must incorporate ways to protect AVs against what must be assumed to be inevitable cyberattacks to meet the overall AV functional safety requirements. This paper investigates the connection between functional safety and cybersecurity in the context of OS. This study finds that risks due to delays can worsen by potential cybersecurity vulnerabilities through a case example of an automated vehicle following. Furthermore, attack surfaces and cybersecurity countermeasures for protecting OSs from security breaches are addressed.

Over recent years, we have seen a significant rise in popularity of autonomous vehicle. Several researches have shown the severity of security threats that autonomous vehicles face -for example, Miller and Valasek (2015) were able to remotely take complete control over a 2014 Jeep Cherokee in a so called "Jeephack" [1]. This paper analyses the threats that the Electrical and Electronic (E/E) architecture of an autonomous vehicle has to face and rank those threats by severity. To achieve this, the Microsoft's STRIDE threat analysis technique was applied and 13 threats were identified. These are sorted by their Common Vulnerability Scoring System (CVSS) scores. Potential mitigation methods are then suggested for the five topmost severe threats.

In a previous article [1] we proposed a layered framework to support the assessment of the security risks associated with the use of autonomous vehicles in military operations and determine how to manage these risks appropriately. We established consistent terminology and defined the problem space, while exploring the first layer of the framework, namely risks from the mission assurance perspective. In this paper, we develop the second layer of the framework. This layer focuses on the risk assessment of the vehicles themselves and on producing a highlevel security design adequate for the mission defined in the first layer. To support this process, we also define a reference model for autonomous vehicles to use as a common basis for the assessment of risks and the design of the security controls.

Improved safety, high mobility and environmental concerns in transportation systems across the world and the corresponding developments in information and communication technologies continue to drive attention towards Intelligent Transportation Systems (ITS). This is evident in advanced driver-assistance systems such as lane departure warning, adaptive cruise control and collision avoidance. However, in connected and autonomous vehicles, the efficient functionality of these applications depends largely on the ability of a vehicle to accurately predict it operating parameters such as location and speed. The ability to predict the immediate future/next location (or speed) of a vehicle or its ability to predict neighbors help in guaranteeing integrity, availability and accountability, thus boosting safety and resiliency of the Vehicular Network for Mobile Cyber Physical Systems (VCPS). In this paper, we proposed a secure movement-prediction for connected vehicles by using Kalman filter. Specifically, Kalman filter predicts the locations and speeds of individual vehicles with reference to already observed and known information such posted legal speed limit, geographic/road location, direction etc. The aim is to achieve resilience through the predicted and exchanged information between connected moving vehicles in an adaptive manner. By being able to predict their future locations, the following vehicle is able to adjust its position more accurately to avoid collision and to ensure optimal information exchange among vehicles.

With self-driving cars making their way on to our roads, we ask not what it would take for them to gain acceptance among consumers, but what impact they may have on other drivers. How they will be perceived and whether they will be trusted will likely have a major effect on traffic flow and vehicular safety. This work first undertakes an exploratory factor analysis to validate a trust scale for human-robot interaction and shows how previously validated metrics and general trust theory support a more complete model of trust that has increased applicability in the driving domain. We experimentally test this expanded model in the context of human-automation interaction during simulated driving, revealing how using these dimensions uncovers significant biases within human-robot trust that may have particularly deleterious effects when it comes to sharing our future roads with automated vehicles.

This study investigates how risk influences users' trust before and after interactions with technologies such as autonomous vehicles (AVs'). Also, the psychophysiological correlates of users' trust from users” eletrodermal activity responses. Eighteen (18) carefully selected participants embark on a hypothetical trip playing an autonomous vehicle driving game. In order to stay safe, throughout the drive experience under four risk conditions (very high risk, high risk, low risk and no risk) that are based on automotive safety and integrity levels (ASIL D, C, B, A), participants exhibit either high or low trust by evaluating the AVs' to be highly or less trustworthy and consequently relying on the Artificial intelligence or the joystick to control the vehicle. The result of the experiment shows that there is significant increase in users' trust and user's delegation of controls to AVs' as risk decreases and vice-versa. In addition, there was a significant difference between user's initial trust before and after interacting with AVs' under varying risk conditions. Finally, there was a significant correlation in users' psychophysiological responses (electrodermal activity) when exhibiting higher and lower trust levels towards AVs'. The implications of these results and future research opportunities are discussed.

This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment.

The paper presents a comprehensive model of cybersecurity threats for a system of autonomous and remotely controlled vehicles (AV) in the environment of a smart city. The main focus in the security context is given to the “integrity” property. That property is of higher importance for industrial control systems in comparison with other security properties (availability and confidentiality). The security graph, which is part of the model, is dynamic, and, in real cases, its analysis may require significant computing resources for AV systems with a large number of assets and connections. The simplified example of the security graph for the AV system is presented.

Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference, or can be identified during the validation phase. There-fore, data poisoning attacks during inference (e.g., adversarial attacks) are becoming more popular. However, many of them do not consider the imperceptibility factor in their optimization algorithms, and can be detected by correlation and structural similarity analysis, or noticeable (e.g., by humans) in multi-level security system. Moreover, majority of the inference attack rely on some knowledge about the training dataset. In this paper, we propose a novel methodology which automatically generates imperceptible attack images by using the back-propagation algorithm on pre-trained DNNs, without requiring any information about the training dataset (i.e., completely training data-unaware). We present a case study on traffic sign detection using the VGGNet trained on the German Traffic Sign Recognition Benchmarks dataset in an autonomous driving use case. Our results demonstrate that the generated attack images successfully perform misclassification while remaining imperceptible in both “subjective” and “objective” quality tests.

Cyber-physical systems are an integral component of weapons, sensors and autonomous vehicles, as well as cyber assets directly supporting tactical forces. Mission resilience of tactical networks affects command and control, which is important for successful military operations. Traditional engineering methods for mission assurance will not scale during battlefield operations. Commanders need useful mission resilience metrics to help them evaluate the ability of cyber assets to recover from incidents to fulfill mission essential functions. We develop 6 cyber resilience metrics for tactical network architectures. We also illuminate how psychometric modeling is necessary for future research to identify resilience metrics that are both applicable to the dynamic mission state and meaningful to commanders and planners.

The evolution of smart automobiles and vehicles within the Internet of Things (IoT) - particularly as that evolution leads toward a proliferation of completely autonomous vehicles - has sparked considerable interest in the subject of vehicle/automotive security. While the attack surface is wide, there are patterns of exploitable vulnerabilities. In this study we reviewed, classified according to their attack surface and evaluated some of the common vehicle and infrastructure attack vectors identified in the literature. To remediate these attack vectors, specific technical recommendations have been provided as a way towards secure deployments of smart automobiles and transportation infrastructures.

Fully autonomous driving is one if not the killer application for the upcoming decade of real-time systems. However, in the presence of increasingly sophisticated attacks by highly skilled and well equipped adversarial teams, autonomous driving must not only guarantee timeliness and hence safety. It must also consider the dependability of the software concerning these properties while the system is facing attacks. For distributed systems, fault-and-intrusion tolerance toolboxes already offer a few solutions to tolerate partial compromise of the system behind a majority of healthy components operating in consensus. In this paper, we present a concept of an intrusion-tolerant architecture for autonomous driving. In such a scenario, predictability and recovery challenges arise from the inclusion of increasingly more complex software on increasingly less predictable hardware. We highlight how an intrusion tolerant design can help solve these issues by allowing timeliness to emerge from a majority of complex components being fast enough, often enough while preserving safety under attack through pre-computed fail safes.

Security is a critical issue for new car generation targeting intelligent transportation systems (ITS), involving autonomous and connected vehicles. In this work we designed a low cost CAN probe and defined analysis tools in order to build attack scenarios. We reuse some threats identified by a previous work. Future researches will address new security protocols.

A term systems of systems (SoS) refers to a setup in which a number of independent systems collaborate to create a value that each of them is unable to achieve independently. Complexity of a SoS structure is higher compared to its constitute systems that brings challenges in analyzing its critical properties such as security. An SoS can be seen as a set of connected systems or services that needs to be adequately protected. Communication between such systems or services can be considered as a service itself, and it is the paramount for establishment of a SoS as it enables connections, dependencies, and a cooperation. Given that reliable and predictable communication contributes directly to a correct functioning of an SoS, communication as a service is one of the main assets to consider. Protecting it from malicious adversaries should be one of the highest priorities within SoS design and operation. This study aims to investigate the attack propagation problem in terms of service-guarantees through the decomposition into sub-services enriched with preconditions and postconditions at the service levels. Such analysis is required as a prerequisite for an efficient SoS risk assessment at the design stage of the SoS development life cycle to protect it from possibly high impact attacks capable of affecting safety of systems and humans using the system.

Fully connected autonomous vehicles are more vulnerable than ever to hacking and data theft. The controller area network (CAN) protocol is used for communication between in-vehicle control networks (IVN). The absence of basic security features of this protocol, like message authentication, makes it quite vulnerable to a wide range of attacks including spoofing attacks. As traditional cybersecurity methods impose limitations in ensuring confidentiality and integrity of transmitted messages via CAN, a new technique has emerged among others to approve its reliability in fully authenticating the CAN messages. At the physical layer of the communication system, the method of fingerprinting the messages is implemented to link the received signal to the transmitting electronic control unit (ECU). This paper introduces a new method to implement the security of modern electric vehicles. The lumped element model is used to characterize the channel-specific step response. ECU and channel imperfections lead to a unique transfer function for each transmitter. Due to the unique transfer function, the step response for each transmitter is unique. In this paper, we use control system parameters as a feature-set, afterward, a neural network is used transmitting node identification for message authentication. A dataset collected from a CAN network with eight-channel lengths and eight ECUs to evaluate the performance of the suggested method. Detection results show that the proposed method achieves an accuracy of 97.4% of transmitter detection.

In this paper, we address the fundamental problem of securely bootstrapping a group of wireless devices to a hub, when none of the devices share prior associations (secrets) with the hub or between them. This scenario aligns with the secure deployment of body area networks, IoT, medical devices, industrial automation sensors, autonomous vehicles, and others. We develop VERSE, a physical-layer group message integrity verification primitive that effectively detects advanced wireless signal manipulations that can be used to launch man-in-the-middle (MitM) attacks over wireless. Without using shared secrets to establish authenticated channels, such attacks are notoriously difficult to thwart and can undermine the authentication and key establishment processes. VERSE exploits the existence of multiple devices to verify the integrity of the messages exchanged within the group. We then use VERSE to build a bootstrapping protocol, which securely introduces new devices to the network. Compared to the state-of-the-art, VERSE achieves in-band message integrity verification during secure pairing using only the RF modality without relying on out-of-band channels or extensive human involvement. It guarantees security even when the adversary is capable of fully controlling the wireless channel by annihilating and injecting wireless signals. We study the limits of such advanced wireless attacks and prove that the introduction of multiple legitimate devices can be leveraged to increase the security of the pairing process. We validate our claims via theoretical analysis and extensive experimentations on the USRP platform. We further discuss various implementation aspects such as the effect of time synchronization between devices and the effects of multipath and interference. Note that the elimination of shared secrets, default passwords, and public key infrastructures effectively addresses the related key management challenges when these are considered at scale.

With increasing automation, occupants of fully autonomous vehicles are likely to be completely disengaged from the driving task. However, even with no driving involved, there are still activities that will require interfaces between the vehicle and passengers. This study evaluated different configurations of screens providing operational-related information to occupants for tracking the progress of journeys. Surveys and interviews were used to measure trust, usability, workload and experience after users were driven by an autonomous low speed pod. Results showed that participants want to monitor the state of the vehicle and see details about the ride, including a map of the route and related information. There was a preference for this information to be displayed via an onboard touchscreen device combined with an overhead letterbox display versus a smartphone-based interface. This paper provides recommendations for the design of devices with the potential to improve the user interaction with future autonomous vehicles.

The fifth generation of cellular networks (5G) will enable different use cases where security will be more critical than ever before (e.g. autonomous vehicles and critical IoT devices). Unfortunately, the new networks are being built on the certainty that security problems cannot be solved in the short term. Far from reinventing the wheel, one of our goals is to allow security software developers to implement and test their reactive solutions for the capillary network of 5G devices. Therefore, in this paper a solution for analysing proximity-based attacks in 5G environments is modelled and tested using OMNET++. The solution, named CRAT, is able to decouple the security analysis from the hardware of the device with the aim to extend the analysis of proximity-based attacks to different use-cases in 5G. We follow a high-level approach, in which the devices can take the role of victim, offender and guardian following the principles of the routine activity theory.