Related papers: Learning-based attacks in cyber-physical systems

We introduce a novel learning-based approach to synthesize safe and robust controllers for autonomous Cyber-Physical Systems and, at the same time, to generate challenging tests. This procedure combines formal methods for model verification…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

Intention deception involves computing a strategy which deceives the opponent into a wrong belief about the agent's intention or objective. This paper studies a class of probabilistic planning problems with intention deception and…

This paper presents a novel data-driven framework to aid in system state estimation when the power system is under unobservable false data injection attacks. The proposed framework dynamically detects and classifies false data injection…

The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm's learning dynamics. While prior work addresses this…

Safety filters ensure that control actions that are executed are always safe, no matter the controller in question. Previous work has proposed a simple and stealthy false-data injection attack for deactivating such safety filters. This…

This paper presents a new framework of identifying a series of cyber data attacks on power system synchrophasor measurements. We focus on detecting "unobservable" cyber data attacks that cannot be detected by any existing method that purely…

Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity,…

Cyber-Physical Systems (CPS) have gained popularity due to the increased requirements on their uninterrupted connectivity and process automation. Due to their connectivity over the network including intranet and internet, dependence on…

Sustainability-targeting attacks (STA) are a growing threat to cyber-physical system (CPS)-based infrastructure, as sustainability goals become an integral part of CPS objectives. STA can be especially disruptive if it impacts the long-term…

Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the triggers are injected. Models trained on the dataset will passively implant the backdoor, and…

We consider the problem of controller design for linear time-invariant cyber-physical systems (CPSs) controlled via networks. Specifically, we adopt the set-up that a controller has already been designed to stabilize the plant. However, the…

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…

We develop a control algorithm that ensures the safety, in terms of confinement in a set, of a system with unknown, 2nd-order nonlinear dynamics. The algorithm establishes novel connections between data-driven and robust, nonlinear control.…

Over the past decade, industrial control systems have experienced a massive integration with information technologies. Industrial networks have undergone numerous technical transformations to protect operational and production processes,…

This paper studies the performance and resilience of a linear cyber-physical control system (CPCS) with attack detection and reactive attack mitigation in the context of power grids. It addresses the problem of deriving an optimal sequence…

In a spoofing attack, an attacker impersonates a legitimate user to access or modify data belonging to the latter. Typical approaches for spoofing detection in the physical layer declare an attack when a change is observed in certain…

A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at deceiving the network, meaning they aim at driving the…

In this work, we investigate how to make use of model reduction techniques to identify the vulnerability of a closed-loop system, consisting of a plant and a supervisor, that might invite attacks. Here, the system vulnerability refers to…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…