NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems

An attack detection scheme is proposed to detect data integrity attacks on sensors in Cyber-Physical Systems (CPSs). A combined fingerprint for sensor and process noise is created during the normal operation of the system. Under sensor spoofing attack, noise pattern deviates from the fingerprinted p...

Descripción completa

Detalles Bibliográficos
Autores Principales: Ahmed C.M., Qadeer R., Ochoa M., Murguia C., Zhou J., Mathur A.P., Ruths J.
Formato: Objeto de conferencia (Conference Object)
Lenguaje:Inglés (English)
Publicado: Association for Computing Machinery, Inc 2018
Materias:
Acceso en línea:https://repository.urosario.edu.co/handle/10336/23055
https://doi.org/10.1145/3196494.3196532
id ir-10336-23055
recordtype dspace
spelling ir-10336-230552022-05-02T12:37:14Z NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems Ahmed C.M. Qadeer R. Ochoa M. Murguia C. Zhou J. Mathur A.P. Ruths J. Actuators Cyber Physical System Embedded systems Frequency domain analysis Learning algorithms Learning systems Sensors State estimation Testbeds Water supply systems Water treatment CPS/ICS Security Cyber physical systems (cpss) Data integrity attacks Device fingerprinting Frequency domains Physical attacks Security Water distributions Palmprint recognition Actuators CPS/ICS Security Cyber Physical Systems Device Fingerprinting Physical Attacks Security Sensors An attack detection scheme is proposed to detect data integrity attacks on sensors in Cyber-Physical Systems (CPSs). A combined fingerprint for sensor and process noise is created during the normal operation of the system. Under sensor spoofing attack, noise pattern deviates from the fingerprinted pattern enabling the proposed scheme to detect attacks. To extract the noise (difference between expected and observed value) a representative model of the system is derived. A Kalman filter is used for the purpose of state estimation. By subtracting the state estimates from the real system states, a residual vector is obtained. It is shown that in steady state the residual vector is a function of process and sensor noise. A set of time domain and frequency domain features is extracted from the residual vector. Feature set is provided to a machine learning algorithm to identify the sensor and process. Experiments are performed on two testbeds, a real-world water treatment (SWaT) facility and a water distribution (WADI) testbed. A class of zero-alarm attacks, designed for statistical detectors on SWaT are detected by the proposed scheme. It is shown that a multitude of sensors can be uniquely identified with accuracy higher than 90% based on the noise fingerprint. © 2018 Association for Computing Machinery. 2018 2020-05-25T23:59:30Z info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion https://repository.urosario.edu.co/handle/10336/23055 https://doi.org/10.1145/3196494.3196532 eng info:eu-repo/semantics/openAccess application/pdf Association for Computing Machinery, Inc instname:Universidad del Rosario
institution EdocUR - Universidad del Rosario
collection DSpace
language Inglés (English)
topic Actuators
Cyber Physical System
Embedded systems
Frequency domain analysis
Learning algorithms
Learning systems
Sensors
State estimation
Testbeds
Water supply systems
Water treatment
CPS/ICS Security
Cyber physical systems (cpss)
Data integrity attacks
Device fingerprinting
Frequency domains
Physical attacks
Security
Water distributions
Palmprint recognition
Actuators
CPS/ICS Security
Cyber Physical Systems
Device Fingerprinting
Physical Attacks
Security
Sensors
spellingShingle Actuators
Cyber Physical System
Embedded systems
Frequency domain analysis
Learning algorithms
Learning systems
Sensors
State estimation
Testbeds
Water supply systems
Water treatment
CPS/ICS Security
Cyber physical systems (cpss)
Data integrity attacks
Device fingerprinting
Frequency domains
Physical attacks
Security
Water distributions
Palmprint recognition
Actuators
CPS/ICS Security
Cyber Physical Systems
Device Fingerprinting
Physical Attacks
Security
Sensors
Ahmed C.M.
Qadeer R.
Ochoa M.
Murguia C.
Zhou J.
Mathur A.P.
Ruths J.
NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
description An attack detection scheme is proposed to detect data integrity attacks on sensors in Cyber-Physical Systems (CPSs). A combined fingerprint for sensor and process noise is created during the normal operation of the system. Under sensor spoofing attack, noise pattern deviates from the fingerprinted pattern enabling the proposed scheme to detect attacks. To extract the noise (difference between expected and observed value) a representative model of the system is derived. A Kalman filter is used for the purpose of state estimation. By subtracting the state estimates from the real system states, a residual vector is obtained. It is shown that in steady state the residual vector is a function of process and sensor noise. A set of time domain and frequency domain features is extracted from the residual vector. Feature set is provided to a machine learning algorithm to identify the sensor and process. Experiments are performed on two testbeds, a real-world water treatment (SWaT) facility and a water distribution (WADI) testbed. A class of zero-alarm attacks, designed for statistical detectors on SWaT are detected by the proposed scheme. It is shown that a multitude of sensors can be uniquely identified with accuracy higher than 90% based on the noise fingerprint. © 2018 Association for Computing Machinery.
format Objeto de conferencia (Conference Object)
author Ahmed C.M.
Qadeer R.
Ochoa M.
Murguia C.
Zhou J.
Mathur A.P.
Ruths J.
author_facet Ahmed C.M.
Qadeer R.
Ochoa M.
Murguia C.
Zhou J.
Mathur A.P.
Ruths J.
author_sort Ahmed C.M.
title NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
title_short NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
title_full NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
title_fullStr NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
title_full_unstemmed NoisePrint: Attack detection using sensor and process noise fingerprint in cyber physical systems
title_sort noiseprint: attack detection using sensor and process noise fingerprint in cyber physical systems
publisher Association for Computing Machinery, Inc
publishDate 2018
url https://repository.urosario.edu.co/handle/10336/23055
https://doi.org/10.1145/3196494.3196532
_version_ 1740172624756998144
score 12,131701