Related papers: Security and Interpretability in Automotive System…

Security verification of communication protocols in industrial and safety-critical systems is challenging because implementations are often proprietary, accessible only as black boxes, and too complex for manual modeling. As a result,…

The deployment of control systems with network-connected components has made feedback control systems vulnerable to attacks over the network. This paper considers the problem of intrusion detection and mitigation in supervisory control…

Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper…

Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other…

As vehicles get equipped with increasingly complex sensors and processors, the communication requirements become more demanding. Traditionally, vehicles have used specialized networking technologies designed to guarantee bounded latencies,…

Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment…

In this paper, we introduce a robust sensor design framework to provide "persuasion-based" defense in stochastic control systems against an unknown type attacker with a control objective exclusive to its type. For effective control, such an…

In this paper, we consider the problem of attack-resilient state estimation, that is to reliably estimate the true system states despite two classes of attacks: (i) attacks on the switching mechanisms and (ii) false data injection attacks…

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

While emerging adaptive cruise control (ACC) technologies are making their way into more vehicles, they also expose a vulnerability to potential malicious cyberattacks. Previous research has typically focused on constant or stochastic…

The Controller Area Network (CAN) is the most common protocol interconnecting the various control units of modern cars. Its vulnerabilities are somewhat known but we argue they are not yet fully explored -- although the protocol is…

Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unforeseen behaviours may occur at any time. While observing the…

Secure message dissemination is an important issue in vehicular networks, especially considering the vulnerability of vehicle to vehicle message dissemination to malicious attacks. Traditional security mechanisms, largely based on message…

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from…

The rapid evolution of smart grids requires effective communication protocols to transfer data reliably and securely. Controller Area Network (CAN) is one of the most recognized protocols that offer reliable data transmission in smart grids…

While the most visible part of the safety verification process of automated vehicles concerns the planning and control system, it is often overlooked that safety of the latter crucially depends on the fault-tolerance of the preceding…

Adaptive Cruise Control (ACC) is a widely used driver assistance technology for maintaining the desired speed and safe distance to the leading vehicle. This paper evaluates the security of the deep neural network (DNN) based ACC systems…

As machine learning models are increasingly deployed in safety-critical domains, visual explanation techniques have become essential tools for supporting transparency. In this work, we reveal a new class of attacks that compromise model…

Deep learning models are known to solve classification and regression problems by employing a number of epoch and training samples on a large dataset with optimal accuracy. However, that doesn't mean they are attack-proof or unexposed to…

Providing safety guarantees for autonomous systems is difficult as these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard…