Related papers: Security Analysis and Fault Detection Against Stea…
Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is…
This paper is concerned with the detection, resilient and fault-tolerant control issues for cyber-physical systems. To this end, the impairment of system dynamics caused by the defined types of cyber-attacks and process faults is analyzed.…
Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical…
Advanced Persistent Threats (APTs) infiltrate cyber systems and compromise specifically targeted data and/or resources through a sequence of stealthy attacks consisting of multiple stages. Dynamic information flow tracking has been proposed…
In this work, we evaluate theoretical results on the feasibility of, the worst-case impact of, and defense mechanisms against a stealthy sensor attack in an experimental setup. We demonstrate that for a controller with stable dynamics the…
We consider the problem of false data injection attacks modeled as additive disturbances in various parts of a general LTI feedback system and derive necessary and sufficient conditions for the existence of stealthy unbounded attacks. We…
Access control mechanisms have been adopted in many real-world systems to control resource sharing for the principals in the system. An error in the access control policy (misconfiguration) can easily cause severe data leakage and system…
Digital twins (DTs) are increasingly used to monitor and secure Industrial Control Systems (ICS), yet detecting stealthy False Data Injection Attacks (FDIAs) that manipulate system states within normal physical bounds remains challenging.…
Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serious data reconstruction attacks. However, existing works lack…
Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors.…
In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy sensor attacks. We start by defining the notion of stealthy attacks in the most general form by leveraging Neyman-Pearson lemma;…
Network systems often contain vulnerabilities that remain unfixed in a network for various reasons, such as the lack of a patch or knowledge to fix them. With the presence of such residual vulnerabilities, the network administrator should…
Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in simulation and often…
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…
Detection-efficiency mismatch is a common problem in practical quantum key distribution (QKD) systems. Current security proofs of QKD with detection-efficiency mismatch rely either on the assumption of the single-photon light source on the…
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 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…
Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge to the practical…
We study the performance of perception-based control systems in the presence of attacks, and provide methods for modeling and analysis of their resiliency to stealthy attacks on both physical and perception-based sensing. Specifically, we…
In the last decade, Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems. However, most RL algorithms rely on the Markov Decision Process assumption, which is violated…