Cooperative multi-agent multi-armed bandits (CMA2B) consider the collaborative efforts of multiple agents in a shared multi-armed bandit game. We study latent vulnerabilities exposed by this collaboration and consider adversarial attacks on a few agents with the goal of influencing the decisions of the rest. More specifically, we study adversarial attacks on CMA2B in both homogeneous settings, where agents operate with the same arm set, and heterogeneous settings, where agents have distinct arm sets. In the homogeneous setting, we propose attack strategies that, by targeting just one agent, convince all agents to select a particular target arm $T-o(T)$ times while incurring $o(T)$ attack costs in $T$ rounds. In the heterogeneous setting, we prove that a target arm attack requires linear attack costs and propose attack strategies that can force a maximum number of agents to suffer linear regrets while incurring sublinear costs and only manipulating the observations of a few target agents. Numerical experiments validate the effectiveness of our proposed attack strategies.

合作多智能体多臂赌博(CMA2B)考虑多个智能体在共享多臂赌博游戏中的协作努力。我们研究了这种合作暴露出的潜在弱点，并考虑对一些智能体进行敌对攻击，以影响其他智能体的决策。我们提出了攻击策略，通过仅针对一个智能体，使所有智能体在选择一个特定目标臂T-o(T)次的同时，承担o(T)次攻击成本，在T轮中产生了攻击策略。在异构设置中，我们证明了对目标臂的攻击需要具有线性攻击成本，并提出了可以迫使最大数量的智能体遭受线性遗憾的攻击策略，同时仅操纵少数目标智能体的观察。数值实验证实了我们提出的攻击策略的有效性。

合作多智能体赌博中的对抗攻击