2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

深度强化学习的攻防与安全性分析综述

陈晋音 章燕 王雪柯 蔡鸿斌 王珏 纪守领

陈晋音, 章燕, 王雪柯, 蔡鸿斌, 王珏, 纪守领. 深度强化学习的攻防与安全性分析综述. 自动化学报, 2022, 48(1): 21−39 doi: 10.16383/j.aas.c200166
引用本文: 陈晋音, 章燕, 王雪柯, 蔡鸿斌, 王珏, 纪守领. 深度强化学习的攻防与安全性分析综述. 自动化学报, 2022, 48(1): 21−39 doi: 10.16383/j.aas.c200166
Chen Jin-Yin, Zhang Yan, Wang Xue-Ke, Cai Hong-Bin, Wang Jue, Ji Shou-Ling. A survey of attack, defense and related security analysis for deep reinforcement learning. Acta Automatica Sinica, 2022, 48(1): 21−39 doi: 10.16383/j.aas.c200166
Citation: Chen Jin-Yin, Zhang Yan, Wang Xue-Ke, Cai Hong-Bin, Wang Jue, Ji Shou-Ling. A survey of attack, defense and related security analysis for deep reinforcement learning. Acta Automatica Sinica, 2022, 48(1): 21−39 doi: 10.16383/j.aas.c200166

深度强化学习的攻防与安全性分析综述

doi: 10.16383/j.aas.c200166
基金项目: 浙江省自然科学基金(LY19F020025), 宁波市“科技创新2025”重大专项(2018B10063), 科技创新2030—“新一代人工智能”重大项目(2018AAA0100800)资助
详细信息
    作者简介:

    陈晋音:浙江工业大学网络空间安全研究院副教授. 2009年获得浙江工业大学博士学位. 主要研究方向为人工智能安全, 网络数据挖掘, 智能计算, 计算机视觉. 本文通信作者.E-mail: chenjinyin@zjut.edu.cn

    章燕:浙江工业大学信息工程学院硕士研究生. 主要研究方向为人工智能安全, 计算机视觉. E-mail: 2111903240@zjut.edu.cn

    王雪柯:浙江工业大学信息工程学院硕士研究生. 主要研究方向为人工智能安全, 计算机视觉. E-mail: 17660478061@163.com

    蔡鸿斌:华东师范大学软件工程学院硕士研究生. 主要研究方向为深度学习. E-mail: hongbincai5330@163.com

    王珏:浙江工业大学信息工程学院硕士研究生. 主要研究方向为人工智能安全, 计算机视觉. E-mail: 211190321@zjut.edu.cn

    纪守领:浙江大学“百人计划”研究员. 2013年获得佐治亚州立大学计算机科学博士学位, 2015年获得佐治亚理工学院电子与计算机工程博士学位. 主要研究方向为数据驱动的安全性和隐私性, 人工智能安全性, 大数据分析. E-mail: sji@zju.edu.cn

A Survey of Attack, Defense and Related Security Analysis for Deep Reinforcement Learning

Funds: Supported by the Zhejiang Provincial Natural Science Foundation of China (LY19F020025), the Major Special Funding for “Science and Technology Innovation 2025” in Ningbo (2018B10063), and the National Key Research and Development Program of China (2018AAA0100800)
More Information
    Author Bio:

    CHEN Jin-Yin Associate professor at the Institute of Cyberspace Security, Zhejiang University of Technology. She received her Ph.D. from Zhejiang University of Technology in 2009. Her research interest covers teaching and scientific research in artificial intelligence security, network data mining, intelligent computing, and computer vision. Corresponding author of thies paper

    ZHANG Yan Master student at the School of Information Engineering, Zhejiang University of Technology. Her research interest covers artificial intelligence security and computer vision

    WANG Xue-Ke Master student at the School of Information Engineering, Zhejiang University of Technology. Her research interest covers artificial intelligence security and computer vision

    CAI Hong-Bin Master student at the School of Software Engineering, East China Normal University. His main research interest is deep learning

    WANG Jue Master student at the School of Information Engineering, Zhejiang University of Technology. His research interest covers artificial intelligence security and computer vision

    JI Shou-Ling Researcher at the “Hundred Talents Program” of Zhejiang University. He received his Ph.D. degree in electrical and computer engineering from Georgia Institute of Technology, and in computer science from Georgia State University in 2013 and 2015, respectively. His research interest covers data-driven security and privacy, artificial intelligence security, and big data analysis

  • 摘要: 深度强化学习是人工智能领域新兴技术之一, 它将深度学习强大的特征提取能力与强化学习的决策能力相结合, 实现从感知输入到决策输出的端到端框架, 具有较强的学习能力且应用广泛. 然而, 已有研究表明深度强化学习存在安全漏洞, 容易受到对抗样本攻击. 为提高深度强化学习的鲁棒性、实现系统的安全应用, 本文针对已有的研究工作, 较全面地综述了深度强化学习方法、对抗攻击、防御方法与安全性分析, 并总结深度强化学习安全领域存在的开放问题以及未来发展的趋势, 旨在为从事相关安全研究与工程应用提供基础.
  • 图  1  对DRL系统的不同类型攻击

    Fig.  1  Different types of attacks on DRL system

    图  2  奖励可视化

    Fig.  2  Reward visualization

    图  3  对抗智能体攻击效果

    Fig.  3  Adversarial agent attack

    图  4  基于预测模型的对抗检测

    Fig.  4  Adversarial detection based on prediction model

    图  5  决策树等价模型验证方法流程

    Fig.  5  Process of decision tree equivalent model verification

    表  1  经典深度强化学习算法对比

    Table  1  Comparison of classic deep reinforcement learning algorithm

    分类算法原理贡献不足
    基于
    值函数
    深度Q网络(DQN)[1-2]使用经验回放机制打破样本相关性; 使用目标网络稳定训练过程第一个能进行端到端学习的
    深度强化学习框架
    训练过程不稳定; 无法处理
    连续动作任务
    双重深度Q网络(DDQN)[3]用目标网络来评估价值, 用评估网络选择动作缓解了DQN对价值的过估计问题训练过程不稳定; 无法
    处理连续动作
    优先经验回放Q网络
    (Prioritized DQN)[4]
    对经验池中的训练样本设立优先级进行采样提高对稀有样本的使用效率训练过程不稳定; 无法
    处理连续动作
    对偶深度Q网络
    (Dueling DQN)[5]
    对偶网络结构, 使用状态价值函数, 与相对动作价值函数来评估Q值存在多个价值相仿的动作时
    提高了评估的准确性
    无法处理连续动作
    深度循环Q网络(DRQN)[27]用长短时记忆网络替换全连接层缓解了部分可观测问题完全可观测环境下性能表现不
    足; 无法处理连续动作
    注意力机制深度循环Q
    网络(DARQN)[28]
    引入注意力机制减轻网络训练的运算代价训练过程不稳定; 无法
    处理连续动作
    噪声深度Q网络
    (Noisy DQN)[29]
    在网络权重中加入参数噪声提高了探索效率; 减少了参数设置; 训练过程不稳定; 无法
    处理连续动作
    循环回放分布式深度
    Q网络(R2D2)[30]
    RNN隐藏状态存在经验池中; 采样部分序列产生RNN初始状态 减缓了RNN状态滞后性状态滞后和表征漂移
    问题仍然存在
    演示循环回放分布式深度
    Q网络(R2D3)[32]
    经验回放机制; 专家演示回放缓冲区; 分布式优先采样 解决了在初始条件高度可变
    的部分观察环境中的
    稀疏奖励任务
    无法完成记住和越过
    传感器的任务
    基于策
    略梯度
    REINFORCE[35]使用随机梯度上升法; 累计奖励作为动作价值函数的无偏估计策略梯度是无偏的存在高方差;收敛速度慢
    自然策略梯度(Natural PG)[36]自然梯度朝贪婪策略方向更新收敛速度更快; 策略更新变化小自然梯度未达到有效最大值
    行动者−评论者(AC)[37]Actor用来更新策略; Critic用来评估策略解决高方差的问题AC算法中策略梯度存
    在较大偏差
    确定性策略梯度(DDPG)[38]确定性策略理论 解决了连续动作问题无法处理离散动作问题
    异步/同步优势行动者−评
    论者(A3C/A2C)[6]
    使用行动者评论者网络结构; 异步更新公共网络参数用多线程提高学习效率;
    降低训练样本的相关性;
    降低对硬件的要求
    内存消耗大; 更新策略
    时方差较大
    信任域策略优化(TRPO)[7]用KL散度限制策略更新保证了策略朝着优化的方向更新实现复杂; 计算开销较大
    近端策略优化(PPO)[39]经过裁剪的替代目标函数自适应的KL惩罚系数比TRPO更容易实现;
    所需要调节的参数较少
    用偏差大的大数据批进行学
    习时无法保证收敛性
    K因子信任域行动者评
    论者算法(ACKTR)[8]
    信任域策略优化; Kronecker因子
    算法; 行动者评论者结构
    采样效率高; 显著减少计算量计算依然较复杂
    下载: 导出CSV

    表  2  深度强化学习的攻击方法

    Table  2  Attack methods toward deep reinforcement learning

    分类攻击方法攻击模型攻击策略攻击阶段对手知识
    观测攻击(见2.1)FGSM[19]DQN[1-2]、TRPO[7]、A3C[6]在观测上加上FGSM攻击测试阶段白盒/黑盒
    策略诱导攻击[41]DQN[1-2]训练敌手策略; 对抗样本的转移性训练阶段黑盒
    战略时间攻击[42]DQN[1-2]、A3C[6]在一些关键时间步进行攻击测试阶段白盒
    迷惑攻击[42]DQN[1-2]、A3C[6]通过预测模型诱导智能体做出动作测试阶段白盒
    基于值函数的对抗攻击[44]A3C[6]在值函数的指导下选择部分观测进行攻击测试阶段白盒
    嗅探攻击[45]DQN[1-2]、PPO[39]用观测以及奖励、动作信号来获取代理模型并进行攻击测试阶段黑盒
    基于模仿学习的攻击[46]DQN[1-2]、A2C[6]、PPO[39]使用模仿学习提取的专家模型信息进行攻击测试阶段黑盒
    CopyCAT算法[47]DQN[1-2]使用预先计算的掩码对智能体的观测做出实时的攻击测试阶段白盒/黑盒
    奖励攻击(见2.2)基于对抗变换网络的对抗攻击[21]DQN[1-2]加入一个前馈的对抗变换网络使策略追求对抗奖励测试阶段白盒
    木马攻击[48]A2C[6]在训练阶段用特洛伊木马进行中毒攻击训练阶段白盒/黑盒
    翻转奖励符号攻击[49]DDQN[3]翻转部分样本的奖励值符号训练阶段白盒
    环境攻击(见2.3)路径脆弱点攻击[50]DQN[1-2]根据路径点Q值的差异与直线的夹角找出脆弱点训练阶段白盒
    通用优势对抗样本生成方法[20]A3C[6]在梯度上升最快的横断面上添加障碍物训练阶段白盒
    对环境模型的攻击[51]DQN[1-2]、DDPG[38]在环境的动态模型上增加扰动测试阶段黑盒
    动作攻击(见2.4)动作空间扰动攻击[52]PPO[39]、DDQN[3]通过奖励函数计算动作空间扰动训练阶段白盒
    策略攻击(见2.5)通过策略进行攻击[53]PPO[39]采用对抗智能体防止目标智能体完成任务测试阶段黑盒
    下载: 导出CSV

    表  3  深度强化学习的攻击和攻击成功率

    Table  3  Attack success rate toward deep reinforcement learning

    攻击模型攻击方法攻击阶段攻击策略平台成功率
    DQN[1]CopyCAT算法[47]测试阶段使用预先计算的掩码对智能体的观测做出实时的攻击OpenAI Gym[77]60%~100%
    FGSM攻击[19]训练阶段在观测上加上FGSM攻击OpenAI Gym[77]90% ~ 100%
    策略诱导攻击[41]训练阶段训练敌手策略; 对抗样本的转移性Grid-World map[40]70%~95%
    战略时间攻击[42]测试阶段在一些关键时间步进行攻击OpenAI Gym[77]40步以内达到70%
    PPO[37]通过策略进行攻击[53]测试阶段采用对抗智能体防止目标智能体完成任务OpenAI Gym[77]玩家智能体成功率下降至62%和45%
    下载: 导出CSV

    表  4  深度强化学习的防御方法

    Table  4  Defense methods of deep reinforcement learning

    分类防御方法防御机制防御目标攻击方法
    对抗训练(见3.1)使用FGSM与随机噪声重训练[44, 55]对正常训练后的策略使用对抗样本
    与随机噪声进行重训练
    状态扰动FGSM、经值函数指导的对抗攻击
    (见2.1)
    基于梯度带的对抗训练[50]用单一的优势对抗样本进行对抗训练环境扰动通用优势对抗样本生成方法(见2.3)
    非连续扰动下的对抗训练[23]以一定的攻击概率在训练样本中加入对抗扰动状态扰动战略时间攻击、经值函数指导的
    对抗攻击(见2.1)
    基于敌对指导探索的对抗训练[56]根据对抗状态动作对的显著性调整对状态扰动战略时间攻击、嗅探攻击(见2.1)
    鲁棒学习(见3.2)基于代理奖励的鲁棒训练[57]通过混淆矩阵得到代理奖励值以
    更新动作价值函数
    奖励扰动结合对抗变换网络的对抗攻击(见2.2)
    鲁棒对抗强化学习[58]在有对抗智能体的情境下利用
    博弈原理进行鲁棒训练
    不同场景下的不稳定因素在多智能体环境下的对抗策略(见2.5)
    二人均衡博弈[59]博弈、均衡原理奖励扰动结合对抗变换网络的对抗攻击(见2.2)
    迭代动态博弈框架[60]用迭代的极大极小动态博弈
    框架提供全局控制
    状态扰动FGSM、战略时间攻击、经值函数指导
    的对抗攻击、迷惑攻击(见2.1)
    对抗A3C[24]在有对抗智能体的情境下
    进行博弈鲁棒训练
    不同场景下的不稳定因素在多智能体环境下的对抗策略(见2.5)
    噪声网络[61]使用参数空间噪声减弱对
    抗样本的迁移能力
    状态扰动FGSM、策略诱导攻击、利用模仿
    学习的攻击(见2.1)
    方差层[62]用权重遵循零均值分布, 并且仅
    由其方差参数化的随机层进行训练
    状态扰动FGSM、战略时间攻击、经值函数
    指导的对抗攻击、迷惑攻击(见2.1)
    对抗检测(见3.3)基于元学习的对抗检测[63]学习子策略以检测对抗扰动的存在状态扰动FGSM、战略时间攻击、经值函数
    指导的对抗攻击、迷惑攻击(见2.1)
    基于预测模型的对抗检测[25]通过比较预测帧与当前帧之间
    的动作分布来检测对抗扰动
    状态扰动FGSM、战略时间攻击、经值函数指导
    的对抗攻击、迷惑攻击(见2.1)
    水印授权[54]在策略中加入特有的水印以
    保证策略不被非法修改
    策略篡改CopyCAT攻击、策略诱导攻击(见2.1)
    受威胁的马尔科夫决策过程[68]在马尔科夫决策过程中加入攻击者
    动作集并使用K级思维模式进行学习
    奖励扰动翻转奖励符号攻击(见2.2)
    在线认证防御[69]在输入扰动范围内选择最优动作状态扰动FGSM、战略时间攻击、经值函数指导
    的对抗攻击、迷惑攻击(见2.1)
    下载: 导出CSV

    表  6  深度强化学习的攻击指标

    Table  6  Attack indicators of deep reinforcement learning

    分类 攻击方法 攻击模型 平台 奖励 损失 成功率 精度
    观测攻击 FGSM[19] DQN[1-2]、TRPO[7]、A3C[6] OpenAI Gym[75]
    策略诱导攻击[41] DQN[1-2] Grid-world[40]
    战略时间攻击[42] DQN[1-2]、A3C[6] OpenAI Gym[75]
    迷惑攻击[42] DQN[1-2]、A3C[6] OpenAI Gym[75]
    基于值函数的对抗攻击[44] A3C[6] OpenAI Gym[75]
    嗅探攻击[45] DQN[1-2]、PPO[39] OpenAI Gym[75]
    基于模仿学习的攻击[46] DQN[1-2]、A2C[6]、PPO[39] OpenAI Gym[75]
    CopyCAT算法[47] DQN[1-2] OpenAI Gym[75]
    奖励攻击 基于对抗变换网络的对抗攻击[21] DQN[1-2] OpenAI Gym[75]
    木马攻击[48] A2C[6] OpenAI Gym[75]
    翻转奖励符号攻击[49] DDQN[3] SDN environment[49]
    环境攻击 路径脆弱点攻击[50] DQN[1-2] OpenAI Gym[75]
    通用优势对抗样本生成方法[20] A3C[6] Grid-world[40]
    对环境模型的攻击[51] DQN[1-2]、DDPG[38] OpenAI Gym[75]
    动作攻击 动作空间扰动攻击[52] PPO[37]、DDQN[3] OpenAI Gym[75]
    策略攻击 通过策略进行攻击[53] PPO[39] OpenAI Gym[75]
    下载: 导出CSV

    表  7  深度强化学习的防御指标

    Table  7  Defense indicators of deep reinforcement learning

    分类 防御方法 实验平台 平均回报 成功率 每回合步数
    对抗训练 使用FGSM与随机噪声重训练[44-45] OpenAI Gym[75]
    基于梯度带的对抗训练[50] Grid-world[40]
    非连续扰动下的对抗训练[56] OpenAI Gym[75]
    基于敌对指导探索的对抗训练[57] OpenAI Gym[75]
    鲁棒学习 基于代理奖励的鲁棒训练[58] OpenAI Gym[75]
    鲁棒对抗强化学习[59] OpenAI Gym[75]
    二人均衡博弈[60] Grid-world[40]
    迭代动态博弈框架[61] KUKA youbot[60]
    对抗A3C[24] OpenAI Gym[75]
    噪声网络[62] OpenAI Gym[75]
    方差层[63] OpenAI Gym[75]
    对抗检测 基于元学习的对抗检测[64] OpenAI Gym[75]
    基于预测模型的对抗检测[25] OpenAI Gym[75]
    水印授权[54] OpenAI Gym[75]
    受威胁的马尔科夫决策过程[69] Grid-world[40]
    在线认证防御[70] OpenAI Gym[75]
    下载: 导出CSV

    表  5  深度强化学习的安全性评估指标

    Table  5  Security evaluation indicators of deep reinforcement learning

    分类指标评价机制评价目的
    攻击指标奖励根据模型策略运行多个回合, 计算累积回合奖励或者平均回合奖励用于评估攻击方法对模型整体性能的影响
    损失通过定义含有物理意义的概念来计算其是否到达不安全或者失败场景用于评估攻击方法对模型策略的影响
    成功率攻击方法在一定限制条件内可以达到成功攻击的次数比例用于评估攻击方法的有效性
    精度模型输出的对抗点中可以成功干扰路径规划的比例用于评估攻击方法对模型策略的影响
    防御指标平均回报根据模型策略运行多个回合, 计算平均回合奖励用于评估防御方法对提高模型性能的有效性
    成功率检测攻击者篡改的策略动作用于评估防御方法的有效性
    每回合步数根据模型策略运行多个回合, 记录每个回合的存活步数或者平均回合步数用于评估防御方法对提高模型性能的有效性
    下载: 导出CSV
  • [1] Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra  D,  et  al.  Playing  atari  with  deep  reinforcement learning. arXiv preprint arXiv: 1312.5602, 2013
    [2] Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, et al. Human-level control through deep reinforcement learning. Nature, 2015, 518(7540): 529-533 doi: 10.1038/nature14236
    [3] Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double Q-learning. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix, Arizona: AAAI, 2016. 2094−2100
    [4] Schaul T, Quan J, Antonoglou I, Silver D. Prioritized experience replay. arXiv preprint arXiv: 1511.05952, 2016
    [5] Wang Z Y, Schaul T, Hessel M, van Hasselt H, Lanctot M, de Freitas N. Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv: 1511.06581, 2016
    [6] Mnih V, Badia A P, Mirza M, Graves A, Harley T, Lillicrap T P, et al. Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning. New York, NY, USA: JMLR.org, 2016. 1928−1937
    [7] Schulman J, Levine S, Moritz P, Jordan M, Abbeel P. Trust region policy optimization. In: Proceedings of the 31st International Conference on Machine Learning. Lille, France: JMLR, 2015. 1889−1897
    [8] Wu Y H, Mansimov E, Liao S, Grosse R, Ba J. Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, California, USA: Curran Associates Inc., 2017. 5285−5294
    [9] Silver D, Huang A, Maddison C J, Guez A, Sifre L, Van Den driessche G, et al. Mastering the game of Go with deep neural networks and tree search. Nature, 2016, 529(7587): 484-489 doi: 10.1038/nature16961
    [10] Berner C, Brockman G, Chan B, Cheung V, Dȩbiak P, Dennison C, et al. Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv: 1912.06680, 2019
    [11] Fayjie A R, Hossain S, Oualid D, Lee D J. Driverless car: Autonomous driving using deep reinforcement learning in urban environment. In: Proceedings of the 15th International Conference on Ubiquitous Robots (UR). Honolulu, HI, USA: IEEE, 2018. 896−901
    [12] Prasad N, Cheng L F, Chivers C, Draugelis M, Engelhardt B E. A reinforcement learning approach to weaning of mechanical ventilation in intensive care units. arXiv preprint arXiv: 1704.06300, 2017
    [13] Deng Y, Bao F, Kong Y Y, Ren Z Q, Dai Q H. Deep direct reinforcement learning for financial signal representation and trading. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(3): 653-664 doi: 10.1109/TNNLS.2016.2522401
    [14] Amarjyoti S. Deep reinforcement learning for robotic manipulation-the state of the art. arXiv preprint arXiv: 1701.08878, 2017
    [15] Nguyen T T, Reddi V J. Deep reinforcement learning for cyber security. arXiv preprint arXiv: 1906.05799, 2020
    [16] Oh J, Guo X X, Lee H, Lewis R, Singh S. Action-conditional video prediction using deep networks in Atari games. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press, 2015. 2863−2871
    [17] Caicedo J C, Lazebnik S. Active object localization with deep reinforcement learning. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE, 2015. 2488−2496
    [18] Sutton R S, Barto A G. Reinforcement Learning: An Introduction (Second Edition). Cambridge, MA: MIT Press, 2018. 47−48
    [19] Huang S, Papernot N, Goodfellow I, Duan Y, Abbeel P. Adversarial attacks on neural network policies. arXiv preprint arXiv: 1702.02284, 2017
    [20] Chen T, Niu W J, Xiang Y X, Bai X X, Liu J Q, Han Z, et al. Gradient band-based adversarial training for generalized attack immunity of A3C path finding. arXiv preprint arXiv: 1807.06752, 2018
    [21] Tretschk E, Oh S J, Fritz M. Sequential attacks on agents for long-term adversarial goals. arXiv preprint arXiv: 1805.12487, 2018
    [22] Ferdowsi A, Challita U, Saad W, Mandayam N B. Robust deep reinforcement learning for security and safety in autonomous vehicle systems. In: Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, HI, USA: IEEE, 2018. 307−312
    [23] Behzadan V, Munir A. Whatever does not kill deep reinforcement learning, makes it stronger. arXiv preprint arXiv: 1712.09344, 2017
    [24] Gu Z Y, Jia Z Z, Choset H. Adversary A3C for robust reinforcement learning. arXiv preprint arXiv: 1912.00330, 2019
    [25] Lin Y C, Liu M Y, Sun M, Huang J B. Detecting adversarial attacks on neural network policies with visual foresight. arXiv preprint arXiv: 1710.00814, 2017
    [26] Watkins C J C H, Dayan P. Q-learning. Machine learning, 1992, 8(3−4): 279−292
    [27] Hausknecht M, Stone P. Deep recurrent Q-learning for partially observable MDPs. In: Proceedings of 2015 AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents. Arlington, Virginia, USA: AAAI, 2015.
    [28] Sorokin I, Seleznev A, Pavlov M, Fedorov A, Ignateva A. Deep attention recurrent Q-network. arXiv preprint arXiv: 1512.01693, 2015
    [29] Plappert M, Houthooft R, Dhariwal P, Sidor S, Chen R Y, Chen X, et al. Parameter space noise for exploration. arXiv preprint arXiv: 1706.01905, 2018
    [30] Kapturowski S, Ostrovski G, Quan J, Munos R, Dabney W. Recurrent experience replay in distributed reinforcement learning. In: Proceedings of the 7th International Conference on Learning Representations. New Orleans, LA, USA, 2019.
    [31] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780 doi: 10.1162/neco.1997.9.8.1735
    [32] Le Paine T, Gulcehre C, Shahriari B, Denil M, Hoffman M, Soyer H, et al. Making efficient use of demonstrations to solve hard exploration problems. arXiv preprint arXiv: 1909.01387, 2019
    [33] Sutton R S, McAllester D A, Singh S, Mansour Y. Policy gradient methods for reinforcement learning with function approximation. In: Proceedings of the 12th International Conference on Neural Information Processing Systems. Denver, CO: MIT Press, 1999. 1057−1063
    [34] Silver D, Lever G, Heess N, et al. Deterministic policy gradient algorithms. In: Proceedings of the International conference on machine learning. PMLR, 2014: 387−395
    [35] Graf T, Platzner M. Adaptive playouts in monte-carlo tree search with policy-gradient reinforcement learning. In: Proceedings of the 14th International Conference on Advances in Computer Games. Leiden, The Netherlands: Springer, 2015. 1−11
    [36] Kakade S M. A natural policy gradient. In: Advances in Neural Information Processing Systems 14. Vancouver, British Columbia, Canada: MIT Press, 2001. 1531−1538
    [37] Konda V R, Tsitsiklis J N. Actor-critic algorithms. In: Advances in Neural Information Processing Systems 14. Vancouver, British Columbia, Canada: MIT Press, 2001. 1008−1014
    [38] Lillicrap T P, Hunt J J, Pritzel A, Heess N, Erez T, Tassa Y, et al. Continuous control with deep reinforcement learning. arXiv preprint arXiv: 1509.02971, 2019
    [39] Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O. Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347, 2017
    [40] Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. arXiv preprint arXiv: 1412.6572, 2015
    [41] Behzadan V, Munir A. Vulnerability of deep reinforcement learning to policy induction attacks. In: Proceedings of the 13th International Conference on Machine Learning and Data Mining in Pattern Recognition. New York, NY, USA: Springer, 2017. 262−275
    [42] Lin Y C, Hong Z W, Liao Y H, Shih M L, Liu M Y, Sun M. Tactics of adversarial attack on deep reinforcement learning agents. arXiv preprint arXiv: 1703.06748, 2019
    [43] Carlini N, Wagner D. MagNet and “efficient defenses against adversarial attacks” are not robust to adversarial examples. arXiv preprint arXiv: 1711.08478, 2017
    [44] Kos J, Song D. Delving into adversarial attacks on deep policies. arXiv preprint arXiv: 1705.06452, 2017
    [45] Inkawhich M, Chen Y R, Li H. Snooping attacks on deep reinforcement learning. arXiv preprint arXiv: 1905.11832, 2020
    [46] Behzadan V, Hsu W. Adversarial exploitation of policy imitation. arXiv preprint arXiv: 1906.01121, 2019
    [47] Hussenot L, Geist M, Pietquin O. CopyCAT: Taking control of neural policies with constant attacks. arXiv preprint arXiv: 1905.12282, 2020
    [48] Kiourti P, Wardega K, Jha S, Li W C. TrojDRL: Trojan attacks on deep reinforcement learning agents. arXiv preprint arXiv: 1903.06638, 2019
    [49] Han Y, Rubinstein B I P, Abraham T, Alpcan T, De Vel O, Erfani S, et al. Reinforcement learning for autonomous defence in software-defined networking. In: Proceedings of the 9th International Conference on Decision and Game Theory for Security. Seattle, WA, USA: Springer, 2018. 145−165
    [50] Bai X X, Niu W J, Liu J Q, Gao X, Xiang Y X, Liu J J. Adversarial examples construction towards white-box Q table variation in DQN pathfinding training. In: Proceedings of the 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC). Guangzhou, China: IEEE, 2018. 781−787
    [51] Xiao C W, Pan X L, He W R, Peng J, Sun M J, Yi J F, et al. Characterizing attacks on deep reinforcement learning. arXiv preprint arXiv: 1907.09470, 2019
    [52] Lee X Y, Ghadai S, Tan K L, Hegde C, Sarkar S. Spatiotemporally constrained action space attacks on deep reinforcement learning agents. arXiv preprint arXiv: 1909.02583, 2019
    [53] Gleave A, Dennis M, Wild C, Kant N, Levine S, Russell S. Adversarial policies: Attacking deep reinforcement learning. arXiv preprint arXiv: 1905.10615, 2021
    [54] Behzadan V, Hsu W. Sequential triggers for watermarking of deep reinforcement learning policies. arXiv preprint arXiv: 1906.01126, 2019
    [55] Pattanaik A, Tang Z Y, Liu S J, Bommannan G, Chowdhary G. Robust deep reinforcement learning with adversarial attacks. In: Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems. Stockholm, Sweden: International Foundation for Autonomous Agents and Multiagent Systems, 2018. 2040−2042
    [56] Behzadan V, Hsu W. Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE). arXiv preprint arXiv: 1906.01119, 2019
    [57] Wang J K, Liu Y, Li B. Reinforcement learning with perturbed rewards. arXiv preprint arXiv: 1810.01032, 2020
    [58] Pinto L, Davidson J, Sukthankar R, Gupta A. Robust adversarial reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70. Sydney, Australia: JMLR.org, 2017. 2817−2826
    [59] Bravo M, Mertikopoulos P. On the robustness of learning in games with stochastically perturbed payoff observations. Games and Economic Behavior, 2017, 103: 41-66 doi: 10.1016/j.geb.2016.06.004
    [60] Ogunmolu O, Gans N, Summers T. Minimax iterative dynamic game: Application to nonlinear robot control tasks. In: Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid, Spain: IEEE, 2018. 6919−6925
    [61] Behzadan V, Munir A. Mitigation of policy manipulation attacks on deep Q-networks with parameter-space noise. In: Proceedings of the International Conference on Computer Safety, Reliability, and Security. Västeras, Sweden: Springer, 2018. 406−417
    [62] Neklyudov K, Molchanov D, Ashukha A, Vetrov D. Variance networks: When expectation does not meet your expectations. arXiv preprint arXiv: 1803.03764, 2019
    [63] Havens A, Jiang Z, Sarkar S. Online robust policy learning in the presence of unknown adversaries. In: Proceedings of the 32nd Conference on Neural Information Processing Systems. Montreal, Canada: Curran Associates, Inc., 2018. 9916−9926
    [64] Xu W L, Evans D, Qi Y J. Feature squeezing mitigates and detects Carlini/Wagner adversarial examples. arXiv preprint arXiv: 1705.10686, 2017
    [65] Meng D Y, Chen H. MagNet: A two-pronged defense against adversarial examples. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. Dallas, Texas, USA: ACM, 2017. 135−147
    [66] Feinman R, Curtin R R, Shintre S, Gardner A B. Detecting adversarial samples from artifacts. arXiv preprint arXiv: 1703.00410, 2017
    [67] Uchida Y, Nagai Y, Sakazawa S, Satoh S. Embedding watermarks into deep neural networks. In: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. Bucharest, Romania: ACM, 2017. 269−277
    [68] Gallego V, Naveiro R, Insua D R. Reinforcement learning under threats. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 9939-9940
    [69] Lütjens B, Everett M, How J P. Certified adversarial robustness for deep reinforcement learning. arXiv preprint arXiv: 1910.12908, 2020
    [70] Athalye A, Carlini N, Wagner D. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. arXiv preprint arXiv: 1802.00420, 2018
    [71] Bastani O, Pu Y W, Solar-Lezama A. Verifiable reinforcement learning via policy extraction. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montreal, Canada: Curran Associates Inc., 2018. 2499−2509
    [72] Zhu H, Xiong Z K, Magill S, Jagannathan S. An inductive synthesis framework for verifiable reinforcement learning. In: Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation. Phoenix, AZ, USA: ACM, 2019. 686−701
    [73] Behzadan V, Munir A. Adversarial reinforcement learning framework for benchmarking collision avoidance mechanisms in autonomous vehicles. arXiv preprint arXiv:1806.01368, 2018
    [74] Behzadan V, Hsu W. RL-based method for benchmarking the adversarial resilience and robustness of deep reinforcement learning policies. arXiv preprint arXiv: 1906.01110, 2019
    [75] Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, et al. OpenAI gym. arXiv preprint arXiv: 1606.01540, 2016
    [76] Johnson M, Hofmann K, Hutton T, Bignell D. The Malmo platform for artificial intelligence experimentation. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). New York, USA: AAAI, 2016. 4246−4247
    [77] Lanctot M, Lockhart E, Lespiau J B, Zambaldi V, Upadhyay S, Pérolat J, et al. OpenSpiel: A framework for reinforcement learning in games. arXiv preprint arXiv: 1908.09453, 2020
    [78] James S, Ma Z C, Arrojo D R, Davison A J. Rlbench: The robot learning benchmark & learning environment. IEEE Robotics and Automation Letters, 2020, 5(2): 3019-3026 doi: 10.1109/LRA.2020.2974707
    [79] Todorov E, Erez T, Tassa Y. MuJoCo: A physics engine for model-based control. In: Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura-Algarve, Portugal: IEEE, 2012. 5026−5033
    [80] Dhariwal P, Hesse C, Klimov O, et al. Openai baselines. 2017.
    [81] Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P. Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the 33rd International Conference on Machine Learning. New York, USA: JMLR.org, 2016. 1329−1338
    [82] Castro P S, Moitra S, Gelada C, Kumar S, Bellemare M G. Dopamine: A research framework for deep reinforcement learning. arXiv preprint arXiv: 1812.06110, 2018
    [83] Papernot N, Faghri F, Carlini N, Goodfellow I, Feinman R, Kurakin A, et al. Technical report on the cleverhans v2.1.0 adversarial examples library. arXiv preprint arXiv: 1610.00768, 2018
    [84] Rauber J, Brendel W, Bethge M. Foolbox: A python toolbox to benchmark the robustness of machine learning models. arXiv preprint arXiv: 1707.04131, 2018
  • 加载中
图(5) / 表(7)
计量
  • 文章访问数:  2769
  • HTML全文浏览量:  2289
  • PDF下载量:  1115
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-04-01
  • 录用日期:  2020-09-07
  • 网络出版日期:  2021-12-21
  • 刊出日期:  2022-01-25

目录

    /

    返回文章
    返回