相关论文: Synthesis of Maximally Permissive Covert Attackers…

Objective: To obtain explainable guarantees in the online synthesis of optimal controllers for high-integrity cyber-physical systems, we re-investigate the use of exhaustive search as an alternative to reinforcement learning. Approach: We…

Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constraint), suitable for interpreting the vulnerability of DNNs.…

We study how to secure distributed filters for linear time-invariant systems with bounded noise under false-data injection attacks. A malicious attacker is able to arbitrarily manipulate the observations for a time-varying and unknown…

One of the main drawbacks while implementing the interaction between a plant and a supervisor, synthesised by the supervisory control theory of \citeauthor{RW:1987}, is the inexact synchronisation. \citeauthor{balemiphdt} was the first to…

We consider the distributed $H_\infty$ estimation problem with an additional requirement of resilience to biasing attacks. An attack scenario is considered where an adversary misappropriates some of the observer nodes and injects biasing…

This paper introduces a novel recursive distributed estimation algorithm aimed at synthesizing input and state interval observers for nonlinear bounded-error discrete-time multi-agent systems. The considered systems have sensors and…

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

In this work, we present a compositional safety controller synthesis approach for the class of discrete-time linear control systems. Here, we leverage a state-of-the-art result on the computation of robust controlled invariant sets. To…

This paper develops a controller synthesis approach for a multi-agent system (MAS) with intermittent communication. We adopt a leader-follower scheme, where a mobile leader with absolute position sensors switches among a set of followers…

Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original image, thereby making…

Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…

The maximization of reach-avoid probabilities for stochastic systems is a central topic in the control literature. Yet, the available methods are either restricted to low-dimensional systems or suffer from conservative approximations. To…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…

Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Despite the impressive progress in the field of presentation attack detection and multimedia forensics over the last decade, these systems are still vulnerable to attacks in real-life settings. Some of the challenges for existing solutions…

We introduce a framework for the control of discrete-time switched stochastic systems with uncertain distributions. In particular, we consider stochastic dynamics with additive noise whose distribution lies in an ambiguity set of…

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space…

This paper investigates the problem of synthesizing proactive defense systems in which the defender can allocate deceptive targets and modify the cost of actions for the attacker who aims to compromise security assets in this system. We…