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

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

This paper proposes a worst-case data-driven control architecture capable of ensuring the safety of constrained Cyber-Physical Systems under cyber-attacks while minimizing, whenever possible, potential degradation in tracking performance.…

We consider a recently proposed \emph{supervised distributed computing} paradigm \cite{augustine2025supervised} that extends and refines the standard master-worker paradigm for parallel computations. In this paradigm, there is a supervisor,…

We propose a new defense mechanism against undetected infiltration into controllers in cyber-physical systems. To this end, we cautiously design the outputs of the sensors that monitor the state of the system. Different from the defense…

We consider the problem of securing a given control loop implementation of a cyber-physical system (CPS) in the presence of Man-in-the-Middle attacks on data exchange between plant and controller over a compromised network. To this end,…

Timing information leakage occurs whenever an attacker successfully deduces confidential internal information by observing some timed information such as events with timestamps. Timed automata are an extension of finite-state automata with…

This paper introduces a run-time mechanism for preventing leakage of secure information in distributed systems. We consider a general concurrency language model, where concurrent objects interact by asynchronous method calls and futures.…

Since the advent of SPECTRE, a number of countermeasures have been proposed and deployed. Rigorously reasoning about their effectiveness, however, requires a well-defined notion of security against speculative execution attacks, which has…

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…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Traditional reactive approach of blacklisting botnets fails to adapt to the rapidly evolving landscape of cyberattacks. An automated and proactive approach to detect and block botnet hosts will immensely benefit the industry. Behavioral…

This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a…

Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional…

Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by…

The rapid expansion of Internet use has increased system exposure to cyber threats, with advanced persistent threats (APTs) being especially challenging due to their stealth, prolonged duration, and multi-stage attacks targeting high-value…

Deep learning based automatic modulation classification (AMC) has received significant attention owing to its potential applications in both military and civilian use cases. Recently, data-driven subsampling techniques have been utilized to…

In this paper, we propose a novel framework for modeling and analysis of networked discrete-event systems (DES). We assume that the plant is controlled by a feedback supervisor whose control decisions are subject to communication delays and…

Given a network with the set of vulnerable actuators (and sensors), the security index of an actuator equals the minimum number of sensors and actuators that needs to be compromised so as to conduct a perfectly undetectable attack using the…

This paper proposes a discrete-time event-triggered extremum seeking control scheme for real-time optimization of nonlinear systems. Unlike conventional discrete-time implementations relying on periodic updates, the proposed approach…

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…