BriefGPT.xyz
May, 2019
深度强化学习的窃听攻击
Snooping Attacks on Deep Reinforcement Learning
HTML
PDF
Matthew Inkawhich, Yiran Chen, Hai Li
TL;DR
该研究提出了一种新的威胁模型，即窃听威胁模型，它是针对强化学习的。通过训练代理模型，并利用敌对性示例的可转移性，敌对方在高度受限的威胁模型中仍然可以对目标代理发动毁灭性攻击。
Abstract
adversarial attacks
have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep
reinforcement learning
agents. The existing methods for attacking
→