Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study

James C Ward; Alex Bott; Connor J York; Edmund R Hunt

doi:10.1109/CASE58245.2025.11164143

Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study

James C Ward^*
, Alex Bott
, Connor J York
, Edmund R Hunt^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

27 Downloads (Pure)

Abstract

Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.

Original language	English
Title of host publication	2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	3385-3392
Number of pages	8
ISBN (Electronic)	9798331522469
ISBN (Print)	9798331522476
DOIs	https://doi.org/10.1109/CASE58245.2025.11164143
Publication status	Published - 23 Sept 2025
Event	2025 IEEE 21st International Conference on Automation Science and Engineering - Millennium Biltmore Hotel Los Angeles, Los Angeles, United States Duration: 17 Aug 2025 → 21 Aug 2025 https://2025.ieeecase.org/

Publication series

Name	IEEE International Conference on Automation Science and Engineering (CASE)
Publisher	IEEE
Volume	2025
ISSN (Print)	2161-8070
ISSN (Electronic)	2161-8089

Conference

Conference	2025 IEEE 21st International Conference on Automation Science and Engineering
Abbreviated title	CASE 2025
Country/Territory	United States
City	Los Angeles
Period	17/08/25 → 21/08/25
Internet address	https://2025.ieeecase.org/

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Access to Document

10.1109/CASE58245.2025.11164143Licence: Unspecified

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM) of the article which has been made Open Access under the University of Bristol's Scholarly Works Policy. The final published version (Version of Record) can be found on the publisher's website. The copyright of any third-party content, such as images, remains with the copyright holder.
Accepted author manuscript, 2.96 MBLicence: CC BY

Handle.net

Persistent link

Cite this

Ward, J. C., Bott, A., York, C. J., & Hunt, E. R. (2025). Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study. In 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE) (pp. 3385-3392). (IEEE International Conference on Automation Science and Engineering (CASE); Vol. 2025). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CASE58245.2025.11164143

Ward, James C ; Bott, Alex ; York, Connor J et al. / Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing : A Multi-Robot Patrol Case Study. 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE). Institute of Electrical and Electronics Engineers (IEEE), 2025. pp. 3385-3392 (IEEE International Conference on Automation Science and Engineering (CASE)).

@inproceedings{34005341c51340ca974776c83da17be9,

title = "Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study",

abstract = "Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.",

author = "Ward, \{James C\} and Alex Bott and York, \{Connor J\} and Hunt, \{Edmund R\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE 21st International Conference on Automation Science and Engineering, CASE 2025 ; Conference date: 17-08-2025 Through 21-08-2025",

year = "2025",

month = sep,

day = "23",

doi = "10.1109/CASE58245.2025.11164143",

language = "English",

isbn = "9798331522476",

series = "IEEE International Conference on Automation Science and Engineering (CASE)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "3385--3392",

booktitle = "2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)",

address = "United States",

url = "https://2025.ieeecase.org/",

}

Ward, JC, Bott, A, York, CJ & Hunt, ER 2025, Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study. in 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE). IEEE International Conference on Automation Science and Engineering (CASE), vol. 2025, Institute of Electrical and Electronics Engineers (IEEE), pp. 3385-3392, 2025 IEEE 21st International Conference on Automation Science and Engineering, Los Angeles, California, United States, 17/08/25. https://doi.org/10.1109/CASE58245.2025.11164143

Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study. / Ward, James C; Bott, Alex; York, Connor J et al.
2025 IEEE 21st International Conference on Automation Science and Engineering (CASE). Institute of Electrical and Electronics Engineers (IEEE), 2025. p. 3385-3392 (IEEE International Conference on Automation Science and Engineering (CASE); Vol. 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing

T2 - 2025 IEEE 21st International Conference on Automation Science and Engineering

AU - Ward, James C

AU - Bott, Alex

AU - York, Connor J

AU - Hunt, Edmund R

PY - 2025/9/23

Y1 - 2025/9/23

N2 - Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.

AB - Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.

U2 - 10.1109/CASE58245.2025.11164143

DO - 10.1109/CASE58245.2025.11164143

M3 - Conference Contribution (Conference Proceeding)

SN - 9798331522476

T3 - IEEE International Conference on Automation Science and Engineering (CASE)

SP - 3385

EP - 3392

BT - 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 17 August 2025 through 21 August 2025

ER -

Ward JC, Bott A, York CJ , Hunt ER. Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study. In 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE). Institute of Electrical and Electronics Engineers (IEEE). 2025. p. 3385-3392. (IEEE International Conference on Automation Science and Engineering (CASE)). doi: 10.1109/CASE58245.2025.11164143

Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this