Anomaly behavior analysis for IoT sensors

Jesus Pacheco, Salim Hariri

Research output: Research - peer-reviewArticle

Abstract

The Internet of Things (IoT) will not only connect computers and mobile devices but also interconnect smart buildings, homes, and cities, as well as electrical grids, gas, and water networks, automobiles, airplanes, etc. IoT will lead to the development of a wide range of advanced information services that need to be processed in real time and require large storage and computational power. The integration of IoT with fog and cloud computing not only brings the computational requirements but also enables IoT services to be pervasive, cost-effective, and accessible from anywhere and at anytime. In any IoT application, sensors are indispensable to bring the physical world into the digital world that can be implemented by leveraging fog computing. However, IoT sensors will introduce major security challenges as they contribute to a significant increase in the IoT attack surface. In this paper, we present a methodology to develop an intrusion detection system on the basis of anomaly behavior analysis to detect when a sensor has been compromised and used to provide misinformation. Our preliminary experimental results show that our approach can accurately authenticate sensors on the basis of their behavior and can detect known and unknown sensor attacks with high detection rate and low false alarms.

LanguageEnglish (US)
JournalTransactions on Emerging Telecommunications Technologies
DOIs
StateAccepted/In press - 2017

Fingerprint

Sensors
Internet of things
Fog
Intelligent buildings
Information services
Intrusion detection
Cloud computing
Mobile devices
Automobiles
Aircraft
Gases
Costs
Water

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Anomaly behavior analysis for IoT sensors. / Pacheco, Jesus; Hariri, Salim.

In: Transactions on Emerging Telecommunications Technologies, 2017.

Research output: Research - peer-reviewArticle

@article{ee9fb3a3947e44b4835da4d01d30d509,
title = "Anomaly behavior analysis for IoT sensors",
abstract = "The Internet of Things (IoT) will not only connect computers and mobile devices but also interconnect smart buildings, homes, and cities, as well as electrical grids, gas, and water networks, automobiles, airplanes, etc. IoT will lead to the development of a wide range of advanced information services that need to be processed in real time and require large storage and computational power. The integration of IoT with fog and cloud computing not only brings the computational requirements but also enables IoT services to be pervasive, cost-effective, and accessible from anywhere and at anytime. In any IoT application, sensors are indispensable to bring the physical world into the digital world that can be implemented by leveraging fog computing. However, IoT sensors will introduce major security challenges as they contribute to a significant increase in the IoT attack surface. In this paper, we present a methodology to develop an intrusion detection system on the basis of anomaly behavior analysis to detect when a sensor has been compromised and used to provide misinformation. Our preliminary experimental results show that our approach can accurately authenticate sensors on the basis of their behavior and can detect known and unknown sensor attacks with high detection rate and low false alarms.",
author = "Jesus Pacheco and Salim Hariri",
year = "2017",
doi = "10.1002/ett.3188",
journal = "Transactions on Emerging Telecommunications Technologies",
issn = "2161-5748",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Anomaly behavior analysis for IoT sensors

AU - Pacheco,Jesus

AU - Hariri,Salim

PY - 2017

Y1 - 2017

N2 - The Internet of Things (IoT) will not only connect computers and mobile devices but also interconnect smart buildings, homes, and cities, as well as electrical grids, gas, and water networks, automobiles, airplanes, etc. IoT will lead to the development of a wide range of advanced information services that need to be processed in real time and require large storage and computational power. The integration of IoT with fog and cloud computing not only brings the computational requirements but also enables IoT services to be pervasive, cost-effective, and accessible from anywhere and at anytime. In any IoT application, sensors are indispensable to bring the physical world into the digital world that can be implemented by leveraging fog computing. However, IoT sensors will introduce major security challenges as they contribute to a significant increase in the IoT attack surface. In this paper, we present a methodology to develop an intrusion detection system on the basis of anomaly behavior analysis to detect when a sensor has been compromised and used to provide misinformation. Our preliminary experimental results show that our approach can accurately authenticate sensors on the basis of their behavior and can detect known and unknown sensor attacks with high detection rate and low false alarms.

AB - The Internet of Things (IoT) will not only connect computers and mobile devices but also interconnect smart buildings, homes, and cities, as well as electrical grids, gas, and water networks, automobiles, airplanes, etc. IoT will lead to the development of a wide range of advanced information services that need to be processed in real time and require large storage and computational power. The integration of IoT with fog and cloud computing not only brings the computational requirements but also enables IoT services to be pervasive, cost-effective, and accessible from anywhere and at anytime. In any IoT application, sensors are indispensable to bring the physical world into the digital world that can be implemented by leveraging fog computing. However, IoT sensors will introduce major security challenges as they contribute to a significant increase in the IoT attack surface. In this paper, we present a methodology to develop an intrusion detection system on the basis of anomaly behavior analysis to detect when a sensor has been compromised and used to provide misinformation. Our preliminary experimental results show that our approach can accurately authenticate sensors on the basis of their behavior and can detect known and unknown sensor attacks with high detection rate and low false alarms.

UR - http://www.scopus.com/inward/record.url?scp=85018983412&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018983412&partnerID=8YFLogxK

U2 - 10.1002/ett.3188

DO - 10.1002/ett.3188

M3 - Article

JO - Transactions on Emerging Telecommunications Technologies

T2 - Transactions on Emerging Telecommunications Technologies

JF - Transactions on Emerging Telecommunications Technologies

SN - 2161-5748

ER -