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
  • [1] Falsification of Cyber-Physical Systems with Reinforcement Learning
    Kato, Koki
    Ishikawa, Fuyuki
    Honiden, Shinichi
    2018 IEEE 3RD WORKSHOP ON MONITORING AND TESTING OF CYBER-PHYSICAL SYSTEMS (MT-CPS 2018), 2018, : 5 - 6
  • [2] Automated Adversary-in-the-Loop Cyber-Physical Defense Planning
    Banik, Sandeep
    Ramachandran, Thiagarajan
    Bhattacharya, Arnab
    Bopardikar, Shaunak D.
    ACM TRANSACTIONS ON CYBER-PHYSICAL SYSTEMS, 2023, 7 (03)
  • [3] Distorting an Adversary's View in Cyber-Physical Systems
    Agarwal, Gaurav Kumar
    Karmoose, Mohammed
    Diggavi, Suhas
    Fragouli, Christina
    Tabuada, Paulo
    2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 1476 - 1481
  • [4] Security Analysis of Cyber-Physical Systems Using Reinforcement Learning
    Ibrahim, Mariam
    Elhafiz, Ruba
    SENSORS, 2023, 23 (03)
  • [5] Safety Verification of Cyber-Physical Systems with Reinforcement Learning Control
    Hoang-Dung Tran
    Cai, Feiyang
    Diego, Manzanas Lopez
    Musau, Patrick
    Johnson, Taylor T.
    Koutsoukos, Xenofon
    ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2019, 18 (05)
  • [6] Robust Testing for Cyber-Physical Systems using Reinforcement Learning
    Qin, Xin
    Arechiga, Nikos
    Deshmukh, Jyotirmoy
    Best, Andrew
    2023 21ST ACM-IEEE INTERNATIONAL SYMPOSIUM ON FORMAL METHODS AND MODELS FOR SYSTEM DESIGN, MEMOCODE, 2023, : 36 - 46
  • [7] Reinforcement Learning for Cyber-Physical Security Assessment of Power Systems
    Liu, Xiaorui
    Konstantinou, Charalambos
    2019 IEEE MILAN POWERTECH, 2019,
  • [8] Vulnerability Analysis for Safe Reinforcement Learning in Cyber-Physical Systems
    Jiang, Shixiong
    Li, Mengyu
    Kong, Fanxin
    PROCEEDINGS 15TH ACM/IEEE INTERNATIONAL CONFERENCE ON CYBER-PHYSICAL SYSTEMS, ICCPS 2024, 2024, : 77 - 86
  • [9] Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning
    Akazaki, Takumi
    Liu, Shuang
    Yamagata, Yoriyuki
    Duan, Yihai
    Hao, Jianye
    FORMAL METHODS, 2018, 10951 : 456 - 465
  • [10] Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning
    Yamagata, Yoriyuki
    Liu, Shuang
    Akazaki, Takumi
    Duan, Yihai
    Hao, Jianye
    IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2021, 47 (12) : 2823 - 2840