Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

被引:9
|
作者
Bhattacharya, Arnab [1 ]
Ramachandran, Thiagarajan [1 ]
Banik, Sandeep [3 ]
Dowling, Chase P. [2 ]
Bopardikar, Shaunak D. [3 ]
机构
[1] Pacific Northwest Natl Lab, Optimizat & Control Grp, Richland, WA 99352 USA
[2] Pacific Northwest Natl Lab, Informat Modeling & Analyt Grp, Richland, WA 99352 USA
[3] Michigan State Univ, Elect & Comp Engn, E Lansing, MI 48824 USA
关键词
Adversary Emulation; Reinforcement Learning; Cyber-Physical Security; Hybrid Attack Graph;
D O I
10.1109/isi49825.2020.9280521
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system's resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in cyber-physical systems (CPS) with complex dynamics, vulnerabilities, and operational uncertainties. In this paper, we develop an automated, domain-aware approach to adversary emulation for CPS. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph with cyber (discrete) and physical (continuous) components and related physical dynamics. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion. As a baseline, we also develop a greedy attack algorithm and compare it with the RL procedures. We summarize our findings through a numerical study on sensor deception attacks in buildings to compare the performance and solution quality of the proposed algorithms.
引用
收藏
页码:1 / 6
页数:6
相关论文
共 50 条
  • [31] Automated process recognition architecture for cyber-physical systems
    Repta, Dragos
    Dumitrache, Ioan
    Sacala, Ioan Stefan
    Moisescu, Mihnea Alexandru
    Stanescu, Aurelian Mihai
    Caramihai, Simona Iuliana
    ENTERPRISE INFORMATION SYSTEMS, 2018, 12 (8-9) : 1129 - 1148
  • [32] Architecture for Digital Twin-Based Reinforcement Learning Optimization of Cyber-Physical Systems
    Modrakowski, Elias
    Braun, Niklas
    Hajnorouzi, Mehrnoush
    Eich, Andreas
    Javaheri, Narges
    Doornbos, Richard
    Moritz, Sebastian
    Bikker, Jan-Willem
    van Beek, Rutger
    SOFTWARE ARCHITECTURE: ECSA 2023 TRACKS, WORKSHOPS, AND DOCTORAL SYMPOSIUM, ECSA 2023, CASA 2023, AMP 2023, FAACS 2023, DEMESSA 2023, QUALIFIER 2023, TWINARCH 2023, 2024, 14590 : 257 - 271
  • [33] Quality of Experience in Cyber-Physical Social Systems Based on Reinforcement Learning and Game Theory
    Tsiropoulou, Eirini Eleni
    Kousis, George
    Thanou, Athina
    Lykourentzou, Ioanna
    Papavassiliou, Symeon
    FUTURE INTERNET, 2018, 10 (11):
  • [34] A survey for deep reinforcement learning in markovian cyber-physical systems: Common problems and solutions
    Rupprecht, Timothy
    Wang, Yanzhi
    NEURAL NETWORKS, 2022, 153 : 13 - 36
  • [35] Multiagent Federated Reinforcement Learning for Secure Incentive Mechanism in Intelligent Cyber-Physical Systems
    Xu, Minrui
    Peng, Jialiang
    Gupta, B. B.
    Kang, Jiawen
    Xiong, Zehui
    Li, Zhenni
    Abd El-Latif, Ahmed A.
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (22): : 22095 - 22108
  • [36] Integration of Reinforcement Learning Agent to Reduce Coordinator Limitations in Cyber-Physical Production Systems
    Ouazzani-Chahidi, Abdelaziz
    Jimenez, Jose-Fernando
    Berrah, Lamia
    Loukili, Abdellatif
    SERVICE ORIENTED, HOLONIC AND MULTI-AGENT MANUFACTURING SYSTEMS FOR INDUSTRY OF THE FUTURE, SOHOMA 2023, 2024, 1136 : 164 - 176
  • [37] Deep Q-Network with Reinforcement Learning for Fault Detection in Cyber-Physical Systems
    Jayaprakash, J. Stanly
    Priyadarsini, M. Jasmine Pemeena
    Parameshachari, B. D.
    Karimi, Hamid Reza
    Gurumoorthy, Sasikumar
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2022, 31 (09)
  • [38] Learning Tracking Control for Cyber-Physical Systems
    Wu, Chengwei
    Pan, Wei
    Sun, Guanghui
    Liu, Jianxing
    Wu, Ligang
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (11) : 9151 - 9163
  • [39] Separation of learning and control for cyber-physical systems?
    Malikopoulos, Andreas A.
    AUTOMATICA, 2023, 151
  • [40] Optimal control and learning for cyber-physical systems
    Wan, Yan
    Yang, Tao
    Yuan, Ye
    Lewis, Frank L.
    INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2021, 31 (06) : 1799 - 1802