相关论文: Heterogeneous Roles against Assignment Based Polic…

This paper proposes a new lens for studying threshold games played on networks when the thresholds are heterogeneous. These are games where agents have two possible actions, and prefer action 1 if and only if enough of their neighbours…

Security challenges accompany the efficiency. The pervasive integration of information and communications technologies (ICTs) makes cyber-physical systems vulnerable to targeted attacks that are deceptive, persistent, adaptive and…

In recent years, reinforcement learning has been successful in solving video games from Atari to Star Craft II. However, the end-to-end model-free reinforcement learning (RL) is not sample efficient and requires a significant amount of…

This paper studies the resilience of second-order networked dynamical systems to strategic attacks. We discuss two widely used control laws, which have applications in power networks and formation control of autonomous agents. In the first…

Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where the attacker tries to jailbreak the defender; if self-play…

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…

A defender-attacker-target problem with non-moving target is considered. This problem is modeled by a pursuit-evasion zero-sum differential game with linear dynamics and quadratic cost functional. In this game the pursuer is the defender,…

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of…

Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate…

A conflict between rational and autonomous agents is considered. The paper addresses a differential game of protecting a target in the 3-D space. This problem highlights the strong correlation between the highly dynamic scenario, the…

We explore a scenario involving two sites and a sequential game between a defender and an attacker, where the defender is responsible for securing the sites while the attacker aims to attack them. Each site holds a loss value for the…

We investigate a game-theoretic model of a social system where both the rules of the game and the interaction structure are shaped by the behavior of the agents. We call this type of model, with several types of feedback couplings from the…

We present two zero-sum games modeling situations where one player attacks (or hides in) a finite dimensional nonempty compact set, and the other tries to prevent the attack (or find him). The first game, called patrolling game, corresponds…

With computing now ubiquitous across government, industry, and education, cybersecurity has become a critical component for every organization on the planet. Due to this ubiquity of computing, cyber threats have continued to grow year over…

This work seeks to design decisionmaking rules for autonomous agents to jointly influence and optimize the behavior of teamed human decisionmakers in the presence of an adversary. We study a situation in which computational jobs are…

The achievement of common goals through voluntary efforts of members of a group can be challenged by the high temptation of individual defection. Here, two-person one-goal assurance games are generalized to N-person, M-goal achievement…

Generating competitive strategies and performing continuous motion planning simultaneously in an adversarial setting is a challenging problem. In addition, understanding the intent of other agents is crucial to deploying autonomous systems…

Cyber deception is one of the key approaches used to mislead attackers by hiding or providing inaccurate system information. There are two main factors limiting the real-world application of existing cyber deception approaches. The first…

Recent advances in robotics have enabled the widespread deployment of autonomous robotic systems in complex operational environments, presenting both unprecedented opportunities and significant security problems. Traditional shepherding…

A key challenge in the study of multiagent cooperation is the need for individual agents not only to cooperate effectively, but to decide with whom to cooperate. This is particularly critical in situations when other agents have hidden,…