BriefGPT.xyz
Jan, 2023
多智能体强化学习中的对抗机器学习攻击与防御综述
SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
HTML
PDF
Maxwell Standen, Junae Kim, Claudia Szabo
TL;DR
本文针对多智能体强化学习模型存在的准确防御策略问题，调研了现有防御及攻击方法，提出了攻击向量的新定义，以两种新的框架来解决现有模型中存在的问题，为未来深入研究提供启示。
Abstract
multi-agent reinforcement learning
(MARL) is vulnerable to
adversarial machine learning
(AML) attacks and needs adequate
defences
before i
→