Related papers: On the Stealth of Unbounded Attacks Under Non-Nega…
Reinforcement learning (RL) for the Markov Decision Process (MDP) has emerged in many security-related applications, such as autonomous driving, financial decisions, and drone/robot algorithms. In order to improve the robustness/defense of…
The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…
Utility companies are increasingly leveraging residential demand flexibility and the proliferation of smart/IoT devices to enhance the effectiveness of residential demand response (DR) programs through automated device scheduling. However,…
The application of Deep Learning-based Schemes (DLSs) for detecting False Data Injection Attacks (FDIAs) in smart grids has attracted significant attention. This paper demonstrates that adversarial attacks, carefully crafted FDIAs, can…
Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training…
This paper studies the performance of a feedback control loop closed via an error-free digital communication channel with transmission delay. The system comprises a discrete-time noisy linear time-invariant (LTI) plant whose single…
High-confidence errors in large language models are often treated as fragile failures. We study an alternative: some errors may be false fixed points, locally stable, internally coherent, and confidently wrong. This separates robustness…
The irreversibility of trajectories in stochastic dynamical systems is linked to the structure of their causal representation in terms of Bayesian networks. We consider stochastic maps resulting from a time discretization with interval \tau…
This letter introduces attack-resilient Control Lyapunov Functions (AR-CLFs) and attack-resilient Control Barrier Functions (AR-CBFs) for nonlinear control-affine systems subject to control-input false data injection attacks (FDIA)…
Continuous-variable quantum key distribution protocol using coherent states and heterodyne detection, called No-Switching protocol, is widely used in practical systems due to the simple experimental setup without basis switching and easy…
This paper addresses Fault Tolerant Control (FTC) of Large Power Systems (LPS) subject to sensor failure. Hiding the fault from the controller allows the nominal controller to remain in the loop. We assume specific faults that violate…
Cryptographic research takes software timing side channels seriously. Approaches to mitigate them include constant-time coding and techniques to enforce such practices. However, recent attacks like Meltdown [42], Spectre [37], and…
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…
Covert communication is the undetected transmission of sensitive information over a communication channel. In wireless communication systems, channel impairments such as signal fading present challenges in the effective implementation and…
Federated self-supervised learning (FSSL) combines the advantages of decentralized modeling and unlabeled representation learning, serving as a cutting-edge paradigm with strong potential for scalability and privacy preservation. Although…
We introduce a novel notion of invariance feedback entropy to quantify the state information that is required by any controller that enforces a given subset of the state space to be invariant. We establish a number of elementary properties,…
When traditional pole-dynamics attacks (TPDAs) are implemented with nominal models, model mismatch between exact and nominal models often affects their stealthiness, or even makes the stealthiness lost. To solve this problem, our current…
This study investigates the relationship between resilience of control systems to attacks and the information available to malicious attackers. Specifically, it is shown that control systems are guaranteed to be secure in an asymptotic…
Adding input and output noises for increasing model identification error of finite impulse response (FIR) systems is considered. This is motivated by the desire to protect the model of the system as a trade secret by rendering model…
We provide theoretical guarantees for recursive feasibility and practical exponential stability of the closed-loop system of a feedback linearizable nonlinear system when controlled by a robust data-driven nonlinear predictive control…