Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats

Pavan Kumar Vaddi; Yunfei Zhao; Xiaoxu Diao; Carol Smidts

Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats

Pavan Kumar Vaddi
, Yunfei Zhao
, Xiaoxu Diao
, Carol Smidts

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The increased implementation of digital systems for instrumentation and control in nuclear power plants has given rise to a heightened risk of cyber-attacks. Given the magnitude of the consequences of cyber-attacks on nuclear power plants, it is imperative that research be focused towards detecting and responding to such events. In this paper, an event classifier to differentiate between safety events and cyber-attacks in nuclear power plants is presented. Its underlying concept is to infer the state of the system by observing both physical and network behaviors during an abnormal event and to calculate the probabilities of observing such behavior in different scenarios. These probabilities are in turn used in determining the nature of the observed abnormal event i.e., cyber or safety. The Dynamic Bayesian Networks (DBNs) methodology, which is appropriate for inferring the hidden state of the system from the observed variables through probabilistic reasoning is used to perform this task.

Original language	English
Title of host publication	11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019
Publisher	American Nuclear Society
Pages	1380-1395
Number of pages	16
ISBN (Electronic)	9780894487835
State	Published - 2019
Externally published	Yes
Event	11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019 - Orlando, United States Duration: Feb 9 2019 → Feb 14 2019

Publication series

Name	11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019

Conference

Conference	11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019
Country/Territory	United States
City	Orlando
Period	02/9/19 → 02/14/19

Funding

This research is being performed using funding received from the DOE Office of Nuclear Energy's Nuclear Energy University Program.

Keywords

Cyber-attacks
Dynamic Bayesian Networks
Network behavior
Nuclear power plant
Physical
Safety events

Cite this

Vaddi, P. K., Zhao, Y., Diao, X., & Smidts, C. (2019). Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats. In 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019 (pp. 1380-1395). (11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019). American Nuclear Society.

Vaddi, Pavan Kumar ; Zhao, Yunfei ; Diao, Xiaoxu et al. / Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats. 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019. American Nuclear Society, 2019. pp. 1380-1395 (11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019).

@inproceedings{f9be54d5038c41ad968c55bd181a5264,

title = "Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats",

abstract = "The increased implementation of digital systems for instrumentation and control in nuclear power plants has given rise to a heightened risk of cyber-attacks. Given the magnitude of the consequences of cyber-attacks on nuclear power plants, it is imperative that research be focused towards detecting and responding to such events. In this paper, an event classifier to differentiate between safety events and cyber-attacks in nuclear power plants is presented. Its underlying concept is to infer the state of the system by observing both physical and network behaviors during an abnormal event and to calculate the probabilities of observing such behavior in different scenarios. These probabilities are in turn used in determining the nature of the observed abnormal event i.e., cyber or safety. The Dynamic Bayesian Networks (DBNs) methodology, which is appropriate for inferring the hidden state of the system from the observed variables through probabilistic reasoning is used to perform this task.",

keywords = "Cyber-attacks, Dynamic Bayesian Networks, Network behavior, Nuclear power plant, Physical, Safety events",

author = "Vaddi, \{Pavan Kumar\} and Yunfei Zhao and Xiaoxu Diao and Carol Smidts",

note = "Publisher Copyright: {\textcopyright} 2018 Westinghouse Electric Company LLC All Rights Reserved; 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019 ; Conference date: 09-02-2019 Through 14-02-2019",

year = "2019",

language = "English",

series = "11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019",

publisher = "American Nuclear Society",

pages = "1380--1395",

booktitle = "11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019",

}

Vaddi, PK, Zhao, Y, Diao, X & Smidts, C 2019, Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats. in 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019. 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019, American Nuclear Society, pp. 1380-1395, 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019, Orlando, United States, 02/9/19.

Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats. / Vaddi, Pavan Kumar; Zhao, Yunfei; Diao, Xiaoxu et al.
11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019. American Nuclear Society, 2019. p. 1380-1395 (11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats

AU - Vaddi, Pavan Kumar

AU - Zhao, Yunfei

AU - Diao, Xiaoxu

AU - Smidts, Carol

PY - 2019

Y1 - 2019

N2 - The increased implementation of digital systems for instrumentation and control in nuclear power plants has given rise to a heightened risk of cyber-attacks. Given the magnitude of the consequences of cyber-attacks on nuclear power plants, it is imperative that research be focused towards detecting and responding to such events. In this paper, an event classifier to differentiate between safety events and cyber-attacks in nuclear power plants is presented. Its underlying concept is to infer the state of the system by observing both physical and network behaviors during an abnormal event and to calculate the probabilities of observing such behavior in different scenarios. These probabilities are in turn used in determining the nature of the observed abnormal event i.e., cyber or safety. The Dynamic Bayesian Networks (DBNs) methodology, which is appropriate for inferring the hidden state of the system from the observed variables through probabilistic reasoning is used to perform this task.

AB - The increased implementation of digital systems for instrumentation and control in nuclear power plants has given rise to a heightened risk of cyber-attacks. Given the magnitude of the consequences of cyber-attacks on nuclear power plants, it is imperative that research be focused towards detecting and responding to such events. In this paper, an event classifier to differentiate between safety events and cyber-attacks in nuclear power plants is presented. Its underlying concept is to infer the state of the system by observing both physical and network behaviors during an abnormal event and to calculate the probabilities of observing such behavior in different scenarios. These probabilities are in turn used in determining the nature of the observed abnormal event i.e., cyber or safety. The Dynamic Bayesian Networks (DBNs) methodology, which is appropriate for inferring the hidden state of the system from the observed variables through probabilistic reasoning is used to perform this task.

KW - Cyber-attacks

KW - Dynamic Bayesian Networks

KW - Network behavior

KW - Nuclear power plant

KW - Physical

KW - Safety events

UR - https://www.scopus.com/pages/publications/85071037166

M3 - Conference contribution

AN - SCOPUS:85071037166

T3 - 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019

SP - 1380

EP - 1395

BT - 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019

PB - American Nuclear Society

T2 - 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019

Y2 - 9 February 2019 through 14 February 2019

ER -

Vaddi PK, Zhao Y, Diao X, Smidts C. Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats. In 11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019. American Nuclear Society. 2019. p. 1380-1395. (11th Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2019).

Dynamic Bayesian networks based event-classifier in support for reactor operators in case of cyber-security threats

Abstract

Publication series

Conference

Funding

Keywords

Other files and links

Fingerprint

Cite this