相关论文: Synthesis of Successful Actuator Attackers on Supe…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

We introduce the problem of learning-based attacks in a simple abstraction of cyber-physical systems---the case of a discrete-time, linear, time-invariant plant that may be subject to an attack that overrides the sensor readings and the…

We consider the probabilistic planning problem for a defender (P1) who can jointly query the sensors and take control actions to reach a set of goal states while being aware of possible sensor attacks by an adversary (P2) who has perfect…

Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks, it might not be computationally or informationally feasible…

Robots incurring component failures ought to adapt their behavior to best realize still-attainable goals under reduced capacity. We formulate the problem of planning with actuators known a priori to be susceptible to failure within the…

This paper develops a novel compositional and abstraction-based approach to synthesize edit functions for opacity enforcement in modular discrete event systems. Edit functions alter the output of the system by erasing or inserting events in…

Recently we developed supervisor localization, a top-down approach to distributed control of discrete-event systems. Its essence is the allocation of monolithic (global) control action among the local control strategies of individual…

Considering real-valued clocks in timed automata (TA) makes it a practical modeling framework for discrete-event systems. However, the infinite state space brings challenges to the control of TA. To synthesize a supervisor for TA using the…

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of…

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are…

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…

We study the stability properties of a control system composed of a dynamical plant and a feedback controller, the latter generating control signals that can be compromised by a malicious attacker. We consider two classes of feedback…

This letter proposes a method to integrate auxiliary actuators that enhance the task space capabilities of commercial underactuated systems, leaving the internal certified low level controller untouched. The additional actuators are…

In this work, leader follower consensus objective has been addressed with the synthesis of an event based controller utilizing sliding mode robust control. The schema has been partitioned into two parts viz. finite time consensus problem…

Cyber-physical systems (CPS), such as autonomous vehicles crossing an intersection, are vulnerable to cyber-attacks and their safety-critical nature makes them a target for malicious adversaries. This paper studies the problem of…

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 driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics should be chosen so as to capture the downstream impact of…

Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that extends the attack lifecycle across multiple sessions under…

In this paper, we study feedback dynamical systems with memoryless controllers under imperfect information. We develop an algorithm that searches for "adversarial scenarios", which can be thought of as the strategy for the adversary…

This article introduces the problem of robust event disturbance rejection. Inspired by the design principle of linear output regulation, a control structure based on excitable systems is proposed. Unlike the linear case, contraction of the…