Related papers: A Markov Decision Process Model for Intrusion Tole…

Societies' norms of operation relies on the proper and secure functioning of several critical infrastructures, particularly modern power grid which is also known as smart grid. Smart grid is interwoven with the information and communication…

Classical game-theoretic approaches for multi-agent systems in both the forward policy design problem and the inverse reward learning problem often make strong rationality assumptions: agents perfectly maximize expected utilities under…

Active fault tolerance is essential for robot swarms to retain long-term autonomy. Previous work on swarm fault tolerance focuses on reacting to electro-mechanical faults that are spontaneously injected into robot sensors and actuators.…

Advanced persistent threats (APTs) are stealthy attacks which make use of social engineering and deception to give adversaries insider access to networked systems. Against APTs, active defense technologies aim to create and exploit…

In this paper, we consider the problem of attack-resilient state estimation, that is to reliably estimate the true system states despite two classes of attacks: (i) attacks on the switching mechanisms and (ii) false data injection attacks…

In order to gain access to networks, different types of intrusion attacks have been designed, and the attackers are working on improving them. Computer networks have become increasingly important in daily life due to the increasing reliance…

Whereas classical Markov decision processes maximize the expected reward, we consider minimizing the risk. We propose to evaluate the risk associated to a given policy over a long-enough time horizon with the help of a central limit…

Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…

With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many servers to switch on or off in…

We study automated intrusion prevention using reinforcement learning. Following a novel approach, we formulate the problem of intrusion prevention as an (optimal) multiple stopping problem. This formulation gives us insight into the…

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

Characterizing attacker behavior with respect to Cyber-Physical Systems is important to assuring the security posture and resilience of these systems. Classical cyber vulnerability assessment approaches rely on the knowledge and experience…

One of the most fundamental problems in Markov decision processes is analysis and control synthesis for safety and reachability specifications. We consider the stochastic reach-avoid problem, in which the objective is to synthesize a…

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision…

A model of strategy formulation is used to study how an adaptive attacker learns to overcome a moving target cyber defense. The attacker-defender interaction is modeled as a game in which a defender deploys a temporal platform migration…

The losses arising from a system being hit by cyber attacks can be staggeringly high, but defending against such attacks can also be costly. This work proposes an attack countermeasure selection approach based on cost impact analysis that…

Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack…

Multi-objective Markov decision processes are sequential decision-making problems that involve multiple conflicting reward functions that cannot be optimized simultaneously without a compromise. This type of problems cannot be solved by a…

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…