Neural Network-Based Attack Detection in Nonlinear Networked Control Systems

Haifeng Niu; Jagannathan Sarangapani

doi:10.1109/IJCNN.2016.7727754

Neural Network-Based Attack Detection in Nonlinear Networked Control Systems

Haifeng Niu
, Jagannathan Sarangapani

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

The communication links in networked control systems are vulnerable to various malicious attacks. In this paper, we propose a novel network attack detection scheme that is able to capture the abnormality in the traffic flow caused by a class of attacks targeting at the communication links. We model the network traffic flow in the bottleneck as a nonlinear system with unknown dynamics. By utilizing an observer, network attack detection residual is generated which is used to determine the existence of attacks in the networks when the residual exceeds a predefined threshold. We also revisit an optimal event-triggered controller for the physical system and derive the maximum delay and packet loss that the system can tolerate.

Original language	American English
Journal	Proceedings of the 2016 International Joint Conference on Neural Networks (2016, Vancouver, Canada)
DOIs	https://doi.org/10.1109/IJCNN.2016.7727754
State	Published - Jul 1 2016

Keywords

Computer crime
Control systems
Cyber-attack detection
Cyber-attacks
Event-triggered
Malicious attack
Network attack
Network traffic flow
Network traffic flow control
Network-based attacks
Networked control systems
Neural networks
Nonlinear networked control systems
Physical systems

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/IJCNN.2016.7727754License: Unspecified

https://doi.org/10.1109/IJCNN.2016.7727754

Cite this

@article{640390f94c9749f59f4250821d5cbb86,

title = "Neural Network-Based Attack Detection in Nonlinear Networked Control Systems",

abstract = " The communication links in networked control systems are vulnerable to various malicious attacks. In this paper, we propose a novel network attack detection scheme that is able to capture the abnormality in the traffic flow caused by a class of attacks targeting at the communication links. We model the network traffic flow in the bottleneck as a nonlinear system with unknown dynamics. By utilizing an observer, network attack detection residual is generated which is used to determine the existence of attacks in the networks when the residual exceeds a predefined threshold. We also revisit an optimal event-triggered controller for the physical system and derive the maximum delay and packet loss that the system can tolerate.",

keywords = "Computer crime, Control systems, Cyber-attack detection, Cyber-attacks, Event-triggered, Malicious attack, Network attack, Network traffic flow, Network traffic flow control, Network-based attacks, Networked control systems, Neural networks, Nonlinear networked control systems, Physical systems",

author = "Haifeng Niu and Jagannathan Sarangapani",

year = "2016",

month = jul,

day = "1",

doi = "10.1109/IJCNN.2016.7727754",

language = "American English",

journal = "Proceedings of the 2016 International Joint Conference on Neural Networks (2016, Vancouver, Canada)",

}

TY - JOUR

T1 - Neural Network-Based Attack Detection in Nonlinear Networked Control Systems

AU - Niu, Haifeng

AU - Sarangapani, Jagannathan

PY - 2016/7/1

Y1 - 2016/7/1

N2 - The communication links in networked control systems are vulnerable to various malicious attacks. In this paper, we propose a novel network attack detection scheme that is able to capture the abnormality in the traffic flow caused by a class of attacks targeting at the communication links. We model the network traffic flow in the bottleneck as a nonlinear system with unknown dynamics. By utilizing an observer, network attack detection residual is generated which is used to determine the existence of attacks in the networks when the residual exceeds a predefined threshold. We also revisit an optimal event-triggered controller for the physical system and derive the maximum delay and packet loss that the system can tolerate.

AB - The communication links in networked control systems are vulnerable to various malicious attacks. In this paper, we propose a novel network attack detection scheme that is able to capture the abnormality in the traffic flow caused by a class of attacks targeting at the communication links. We model the network traffic flow in the bottleneck as a nonlinear system with unknown dynamics. By utilizing an observer, network attack detection residual is generated which is used to determine the existence of attacks in the networks when the residual exceeds a predefined threshold. We also revisit an optimal event-triggered controller for the physical system and derive the maximum delay and packet loss that the system can tolerate.

KW - Computer crime

KW - Control systems

KW - Cyber-attack detection

KW - Cyber-attacks

KW - Event-triggered

KW - Malicious attack

KW - Network attack

KW - Network traffic flow

KW - Network traffic flow control

KW - Network-based attacks

KW - Networked control systems

KW - Neural networks

KW - Nonlinear networked control systems

KW - Physical systems

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/3655

UR - https://doi.org/10.1109/IJCNN.2016.7727754

U2 - 10.1109/IJCNN.2016.7727754

DO - 10.1109/IJCNN.2016.7727754

M3 - Article

JO - Proceedings of the 2016 International Joint Conference on Neural Networks (2016, Vancouver, Canada)

JF - Proceedings of the 2016 International Joint Conference on Neural Networks (2016, Vancouver, Canada)

ER -

Neural Network-Based Attack Detection in Nonlinear Networked Control Systems

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this