In the field of multi-agent autonomous transportation, such as automated payload delivery or
highway on-ramp merging, agents routinely exchange knowledge to optimize their shared …

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-
MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will …

This research explores the vulnerability of selective reincarnation, a concept in Multi-Agent
Reinforcement Learning (MARL), in response to observation poisoning attacks. Observation …

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in
real-world, safety-critical applications--making it paramount to ensure the robustness of RL …

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-
MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will …

Various studies have been conducted on Multi-Agent Reinforcement Learning (MARL) to
control multiple agents to drive effectively and safely in a simulation, demonstrating the …

In the domain of cooperative multi-agent reinforcement learning (c-MARL), the deployment
in safety-critical applications necessitates rigorous robustness testing. Despite the …

摘要诸多神经网络模型已被证明极易遭受对抗样本攻击. 对抗样本则是攻击者为模型所恶意构建
的输入, 通过对原始样本输入添加轻微的扰动, 导致其极易被机器学习模型错误分类 …

Artificial Intelligence (hereinafter referred to as AI) systems have recently found great
application and use in various industries, such as data processing, data analysis, and the …

This dissertation analyzes the pressing security and privacy challenges in Multi-Agent
Critical Infrastructures (MACIs), which increasingly integrate cyber-physical system …