相关论文: Learning-based attacks in Cyber-Physical Systems: …
We consider distributed online learning protocols that control the exchange of information between local learners in a round-based learning scenario. The learning performance of such a protocol is intuitively optimal if approximately the…
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to…
Real-time cyber-physical systems depend on deterministic task execution to guarantee safety and correctness. Unfortunately, this determinism can unintentionally expose timing information that enables adversaries to infer task execution…
In this paper, we propose and analyze an attack detection scheme for securing the physical layer of a networked control system against attacks where the adversary replaces the true observations with stationary false data. An independent and…
We consider networked control systems consisting of multiple independent controlled subsystems, operating over a shared communication network. Such systems are ubiquitous in cyber-physical systems, Internet of Things, and large-scale…
The advantages of using communication networks to interconnect controllers and physical plants motivate the increasing number of Networked Control Systems, in industrial and critical infrastructure facilities. However, this integration also…
Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data…
The smart grid is envisioned to significantly enhance the efficiency of energy consumption, by utilizing two-way communication channels between consumers and operators. For example, operators can opportunistically leverage the delay…
In a spoofing attack, an attacker impersonates a legitimate user to access or tamper with data intended for or produced by the legitimate user. In wireless communication systems, these attacks may be detected by relying on features of the…
Real-world attacks can be interpreted as the result of competitive interactions between networks, ranging from predator-prey networks to networks of countries under economic sanctions. Although the purpose of an attack is to damage a target…
This paper studies the attack detection problem in a data-driven and model-free setting, for deterministic systems with linear and time-invariant dynamics. Differently from existing studies that leverage knowledge of the system dynamics to…
The reported work points at developing a practical approach for power transmission planners to secure power networks from potential deliberate attacks. We study the interaction between a system planner (defender) and a rational attacker who…
We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…
We investigate an attack on a machine learning model that predicts whether a person or household will relocate in the next two years, i.e., a propensity-to-move classifier. The attack assumes that the attacker can query the model to obtain…
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…
We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards,…
Many cybersecurity problems that require real-time decision-making based on temporal observations can be abstracted as a sequence modeling problem, e.g., network intrusion detection from a sequence of arriving packets. Existing approaches…
Adversarial environments require agents to navigate a key strategic trade-off: acquiring information enhances situational awareness, but may simultaneously expose them to threats. To investigate this tension, we formulate a…
This paper studies the optimal output-feedback control of a linear time-invariant system where a stochastic event-based scheduler triggers the communication between the sensor and the controller. The primary goal of the use of this type of…
The vast majority of today's critical infrastructure is supported by numerous feedback control loops and an attack on these control loops can have disastrous consequences. This is a major concern since modern control systems are becoming…