Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing

Justin Kur; Jingshu Chen; Jun Huang

doi:10.1109/ASE56229.2023.00161

Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing

Justin Kur
, Jingshu Chen
, Jun Huang

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

Conventional approaches to analyzing industrial control systems have relied on either white-box analysis or black-box fuzzing. However, white-box methods rely on sophisticated domain expertise, while black-box methods suffers from state explosion and thus scales poorly when analyzing real ICS involving a large number of sensors and actuators. To address these limitations, we propose XAI-based gray-box fuzzing, a novel approach that leverages explainable AI and machine learning modeling of ICS to accurately identify a small set of actuators critical to ICS safety, which result in significant reduction of state space without relying on domain expertise. Experiment results show that our method accurately explains the ICS model and significantly speeds-up fuzzing by 64x when compared to conventional black-box methods. © 2023 IEEE.

Original language	English
Title of host publication	Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023
Publisher	IEEE
Pages	1803-1807
ISBN (Electronic)	979-8-3503-2996-4
ISBN (Print)	979-8-3503-2997-1
DOIs	https://doi.org/10.1109/ASE56229.2023.00161
Publication status	Published - 2023
Event	38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023) - European Convention Center Luxembourg (ECCL), Echternach, Luxembourg Duration: 11 Sept 2023 → 15 Sept 2023 https://conf.researchr.org/home/ase-2023

Publication series

Name	Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE
ISSN (Print)	1938-4300
ISSN (Electronic)	2643-1572

Conference

Conference	38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)
Place	Luxembourg
City	Echternach
Period	11/09/23 → 15/09/23
Internet address	https://conf.researchr.org/home/ase-2023

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Research Keywords

Explainable AI
Fuzzing
Industrial Control Systems
Learning based Approaches
Security Attack

Access Output

10.1109/ASE56229.2023.00161

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Kur, J., Chen, J., & Huang, J. (2023). Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing. In Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023 (pp. 1803-1807). (Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE). IEEE. https://doi.org/10.1109/ASE56229.2023.00161

@inproceedings{ea7f6945738548cda7c5cee50ba961bc,

title = "Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing",

abstract = "Conventional approaches to analyzing industrial control systems have relied on either white-box analysis or black-box fuzzing. However, white-box methods rely on sophisticated domain expertise, while black-box methods suffers from state explosion and thus scales poorly when analyzing real ICS involving a large number of sensors and actuators. To address these limitations, we propose XAI-based gray-box fuzzing, a novel approach that leverages explainable AI and machine learning modeling of ICS to accurately identify a small set of actuators critical to ICS safety, which result in significant reduction of state space without relying on domain expertise. Experiment results show that our method accurately explains the ICS model and significantly speeds-up fuzzing by 64x when compared to conventional black-box methods. {\textcopyright} 2023 IEEE.",

keywords = "Explainable AI, Fuzzing, Industrial Control Systems, Learning based Approaches, Security Attack",

author = "Justin Kur and Jingshu Chen and Jun Huang",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023) ; Conference date: 11-09-2023 Through 15-09-2023",

year = "2023",

doi = "10.1109/ASE56229.2023.00161",

language = "English",

isbn = "979-8-3503-2997-1",

series = "Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE",

publisher = "IEEE",

pages = "1803--1807",

booktitle = "Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023",

address = "United States",

url = "https://conf.researchr.org/home/ase-2023",

}

Kur, J, Chen, J & Huang, J 2023, Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing. in Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023. Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE, IEEE, pp. 1803-1807, 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023), Echternach, Luxembourg, 11/09/23. https://doi.org/10.1109/ASE56229.2023.00161

Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing. / Kur, Justin; Chen, Jingshu; Huang, Jun.
Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023. IEEE, 2023. p. 1803-1807 (Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing

AU - Kur, Justin

AU - Chen, Jingshu

AU - Huang, Jun

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2023

Y1 - 2023

N2 - Conventional approaches to analyzing industrial control systems have relied on either white-box analysis or black-box fuzzing. However, white-box methods rely on sophisticated domain expertise, while black-box methods suffers from state explosion and thus scales poorly when analyzing real ICS involving a large number of sensors and actuators. To address these limitations, we propose XAI-based gray-box fuzzing, a novel approach that leverages explainable AI and machine learning modeling of ICS to accurately identify a small set of actuators critical to ICS safety, which result in significant reduction of state space without relying on domain expertise. Experiment results show that our method accurately explains the ICS model and significantly speeds-up fuzzing by 64x when compared to conventional black-box methods. © 2023 IEEE.

AB - Conventional approaches to analyzing industrial control systems have relied on either white-box analysis or black-box fuzzing. However, white-box methods rely on sophisticated domain expertise, while black-box methods suffers from state explosion and thus scales poorly when analyzing real ICS involving a large number of sensors and actuators. To address these limitations, we propose XAI-based gray-box fuzzing, a novel approach that leverages explainable AI and machine learning modeling of ICS to accurately identify a small set of actuators critical to ICS safety, which result in significant reduction of state space without relying on domain expertise. Experiment results show that our method accurately explains the ICS model and significantly speeds-up fuzzing by 64x when compared to conventional black-box methods. © 2023 IEEE.

KW - Explainable AI

KW - Fuzzing

KW - Industrial Control Systems

KW - Learning based Approaches

KW - Security Attack

UR - https://www.scopus.com/pages/publications/85179010049

UR - https://www.scopus.com/pages/publications/85179010049#tab=impact

U2 - 10.1109/ASE56229.2023.00161

DO - 10.1109/ASE56229.2023.00161

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-3503-2997-1

T3 - Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE

SP - 1803

EP - 1807

BT - Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023

PB - IEEE

T2 - 38th IEEE/ACM International Conference on Automated Software Engineering (ASE 2023)

Y2 - 11 September 2023 through 15 September 2023

ER -

Kur J, Chen J, Huang J. Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing. In Proceedings - 2023 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023. IEEE. 2023. p. 1803-1807. (Proceedings - IEEE/ACM International Conference on Automated Software Engineering, ASE). Epub 2023 Nov 8. doi: 10.1109/ASE56229.2023.00161

Scalable Industrial Control System Analysis via XAI-Based Gray-Box Fuzzing

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this