PowerShark: IEEE 802.15.4 mote activity analysis using power traces and neural networks

Vilen Looga; Zhonghong Ou; Yang Deng; Antti Ylä-Jääski

doi:10.1109/GLOCOM.2016.7842163

PowerShark: IEEE 802.15.4 mote activity analysis using power traces and neural networks

Vilen Looga, Zhonghong Ou^*, Yang Deng, Antti Ylä-Jääski

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Analysing the power usage of an Internet of Things (IoT) device is essential in contexts such as smart building, testbed and forensics. For example, in the smart building case, schemes have been proposed to detect and analyse the activity of electric appliances based on the total power usage. In this work, we intend to take this concept a step further and devise a method to analyse the activity of a single IoT device (mote) based on its power usage. To that end, we develop a neural network (NN) based classifier PowerShark that is capable of classifying mote activity based solely on the power usage of the mote, both in online and offline mode. PowerShark can detect radio activity, hardware, operating system (OS), and the MAC layer used. To verify the accuracy of PowerShark, we use power traces from OpenMote and Zolertia Z1 motes, with ContikiOS configured either with ContikiMAC or X-MAC. Experimental results demonstrate the accuracy of our proposed classifier. Specifically, PowerShark can achieve over 95% accuracy in both training and testing phases.

Original language	English
Title of host publication	2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings
Publisher	IEEE
ISBN (Electronic)	9781509013289
DOIs	https://doi.org/10.1109/GLOCOM.2016.7842163
Publication status	Published - 2 Feb 2017
MoE publication type	A4 Article in a conference publication
Event	IEEE Global Communications Conference - Washington, United States Duration: 4 Dec 2016 → 8 Dec 2016 Conference number: 59

Conference

Conference	IEEE Global Communications Conference
Abbreviated title	GLOBECOM
Country	United States
City	Washington
Period	04/12/2016 → 08/12/2016

Access to Document

10.1109/GLOCOM.2016.7842163

Link to publication in Scopus

Fingerprint Dive into the research topics of 'PowerShark: IEEE 802.15.4 mote activity analysis using power traces and neural networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{9c0836d610034ebd8a0c8a0cb90d3d04,

title = "PowerShark: IEEE 802.15.4 mote activity analysis using power traces and neural networks",

abstract = "Analysing the power usage of an Internet of Things (IoT) device is essential in contexts such as smart building, testbed and forensics. For example, in the smart building case, schemes have been proposed to detect and analyse the activity of electric appliances based on the total power usage. In this work, we intend to take this concept a step further and devise a method to analyse the activity of a single IoT device (mote) based on its power usage. To that end, we develop a neural network (NN) based classifier PowerShark that is capable of classifying mote activity based solely on the power usage of the mote, both in online and offline mode. PowerShark can detect radio activity, hardware, operating system (OS), and the MAC layer used. To verify the accuracy of PowerShark, we use power traces from OpenMote and Zolertia Z1 motes, with ContikiOS configured either with ContikiMAC or X-MAC. Experimental results demonstrate the accuracy of our proposed classifier. Specifically, PowerShark can achieve over 95% accuracy in both training and testing phases.",

author = "Vilen Looga and Zhonghong Ou and Yang Deng and Antti Yl{\"a}-J{\"a}{\"a}ski",

year = "2017",

month = feb,

day = "2",

doi = "10.1109/GLOCOM.2016.7842163",

language = "English",

booktitle = "2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "IEEE Global Communications Conference, GLOBECOM ; Conference date: 04-12-2016 Through 08-12-2016",

}

TY - GEN

T1 - PowerShark

T2 - IEEE Global Communications Conference

AU - Looga, Vilen

AU - Ou, Zhonghong

AU - Deng, Yang

AU - Ylä-Jääski, Antti

N1 - Conference code: 59

PY - 2017/2/2

Y1 - 2017/2/2

N2 - Analysing the power usage of an Internet of Things (IoT) device is essential in contexts such as smart building, testbed and forensics. For example, in the smart building case, schemes have been proposed to detect and analyse the activity of electric appliances based on the total power usage. In this work, we intend to take this concept a step further and devise a method to analyse the activity of a single IoT device (mote) based on its power usage. To that end, we develop a neural network (NN) based classifier PowerShark that is capable of classifying mote activity based solely on the power usage of the mote, both in online and offline mode. PowerShark can detect radio activity, hardware, operating system (OS), and the MAC layer used. To verify the accuracy of PowerShark, we use power traces from OpenMote and Zolertia Z1 motes, with ContikiOS configured either with ContikiMAC or X-MAC. Experimental results demonstrate the accuracy of our proposed classifier. Specifically, PowerShark can achieve over 95% accuracy in both training and testing phases.

AB - Analysing the power usage of an Internet of Things (IoT) device is essential in contexts such as smart building, testbed and forensics. For example, in the smart building case, schemes have been proposed to detect and analyse the activity of electric appliances based on the total power usage. In this work, we intend to take this concept a step further and devise a method to analyse the activity of a single IoT device (mote) based on its power usage. To that end, we develop a neural network (NN) based classifier PowerShark that is capable of classifying mote activity based solely on the power usage of the mote, both in online and offline mode. PowerShark can detect radio activity, hardware, operating system (OS), and the MAC layer used. To verify the accuracy of PowerShark, we use power traces from OpenMote and Zolertia Z1 motes, with ContikiOS configured either with ContikiMAC or X-MAC. Experimental results demonstrate the accuracy of our proposed classifier. Specifically, PowerShark can achieve over 95% accuracy in both training and testing phases.

UR - http://www.scopus.com/inward/record.url?scp=85015426265&partnerID=8YFLogxK

U2 - 10.1109/GLOCOM.2016.7842163

DO - 10.1109/GLOCOM.2016.7842163

M3 - Conference contribution

AN - SCOPUS:85015426265

BT - 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings

PB - IEEE

Y2 - 4 December 2016 through 8 December 2016

ER -