Related papers: Learning-based attacks in cyber-physical systems
We implemented and evaluated an automated cyber defense agent. The agent takes security alerts as input and uses reinforcement learning to learn a policy for executing predefined defensive measures. The defender policies were trained in an…
Security issues have gathered growing interest within the control systems community, as physical components and communication networks are increasingly vulnerable to cyber attacks. In this context, recent literature has studied increasingly…
In this paper, we introduce a new vulnerability of cyber-physical systems to malicious attack. It arises when the physical plant, that is modeled as a continuous-time LTI system, is controlled by a digital controller. In the sampled-data…
The emerging wide area monitoring systems (WAMS) have brought significant improvements in electric grids' situational awareness. However, the newly introduced system can potentially increase the risk of cyber-attacks, which may be disguised…
We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the…
This work presents a rigorous analysis of the adverse effects of cyber-physical attacks on discrete-time distributed multi-agent systems, and propose a mitigation approach for attacks on sensors and actuators. First, we show how an attack…
Industrial control systems (ICS), which in many cases are components of critical national infrastructure, are increasingly being connected to other networks and the wider internet motivated by factors such as enhanced operational…
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…
The technological advancements facilitating the rapid development of cyber-physical systems (CPS) also render such systems vulnerable to cyber attacks with devastating effects. Supervisory control is a commonly used control method to…
We study the security of Cyber-Physical Systems (CPS) in the context of the supervisory control layer. Specifically, we propose a general model of a CPS attacker in the framework of discrete event systems and investigate the problem of…
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…
This paper investigates the design of self-triggered control for networked control systems (NCS), where the dynamics of the plant is unknown apriori. To deal with the nature of the self-triggered control, in which state measurements are…
Maintaining the security of control systems in the presence of integrity attacks is a significant challenge. In literature, several possible attacks against control systems have been formulated including replay, false data injection, and…
We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…
An autonomous and resilient controller is proposed for leader-follower multi-agent systems under uncertainties and cyber-physical attacks. The leader is assumed non-autonomous with a nonzero control input, which allows changing the team…
As more attention is paid to security in the context of control systems and as attacks occur to real control systems throughout the world, it has become clear that some of the most nefarious attacks are those that evade detection. The term…
Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning…
Cyber-physical systems integrate computation, communication, and physical capabilities to interact with the physical world and humans. Besides failures of components, cyber-physical systems are prone to malignant attacks, and specific…
We consider the distributed $H_\infty$ estimation problem with additional requirement of resilience to biasing attacks. An attack scenario is considered where an adversary misappropriates some of the observer nodes and injects biasing…
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…