Related papers: Target Defense against Sequentially Arriving Intru…
We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…
This paper explores a multi-agent containment problem, where a fast evader, modeled having constant speed and using constant heading, attempts to escape a circular containment region that is orbited by a slower pursuer with a nonzero…
DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…
This paper investigates a problem of defending safety-critical infrastructure from an adversarial aerial attacker in an urban environment. A circular arc formation of defenders is formed around the attacker, and vector-field based guidance…
Pursuit-evasion games are ubiquitous in nature and in an artificial world. In nature, pursuer(s) and evader(s) are intelligent agents that can learn from experience, and dynamics (i.e., Newtonian or Lagrangian) is vital for the pursuer and…
We propose a dynamical trapping system composed of multiple chasers subject to target-tracking forces utilizing the velocity and position information of a single escaping target. To successfully capture the target, dividing chasers into…
Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…
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…
In the recently introduced network patrolling game, an Attacker carries out an attack on a node of her choice, for a given number m of consecutive periods. The parameter m indicates the difficulty of the attack at a given node. To thwart…
Securing dynamic networks against adversarial actions is challenging because of the need to anticipate and counter strategic disruptions by adversarial entities within complex network structures. Traditional game-theoretic models, while…
With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist malicious attackers who induce large models to jailbreak and generate information…
We revisit the two-player planar target-defense game initially posed by Isaacs where a pursuer (or defender) attempts to guard a target set from an attack by an evader (or attacker). This paper builds on existing analytical solutions to…
In Stackelberg security games when information about the attacker's payoffs is uncertain, algorithms have been proposed to learn the optimal defender commitment by interacting with the attacker and observing their best responses. In this…
This paper studies a stochastic robotic surveillance problem where a mobile robot moves randomly on a graph to capture a potential intruder that strategically attacks a location on the graph. The intruder is assumed to be omniscient: it…
This paper studies a multiplayer reach-avoid differential game in the presence of general polygonal obstacles that block the players' motions. The pursuers cooperate to protect a convex region from the evaders who try to reach the region.…
We study automated intrusion prevention using reinforcement learning. Following a novel approach, we formulate the interaction between an attacker and a defender as an optimal stopping game and let attack and defense strategies evolve…
The existing network attack and defense method can be regarded as game, but most of the game only involves network domain, not multiple domain cyberspace. To address this challenge, this paper proposed a multiple domain cyberspace attack…
This paper studies the deployment of joint moving target defense (MTD) and deception against multi-stage cyberattacks. Given the system equipped with MTD that randomizes between different configurations, we investigate how to allocate a…
In this work, we model Moving Target Defence (MTD) as a partially observable stochastic game between an attacker and a defender. The attacker tries to compromise the system through probing actions, while the defender minimizes the risk by…
This paper investigates the encirclement control problem involving two groups using a non-cooperative differential game approach. The active group seeks to chase and encircle the passive group, while the passive group responds by fleeing…