Anomaly Detection in Embedded Systems Using Power and Memory Side Channels

Jiho Park; Virinchi Roy Surabhi; Prashanth Krishnamurthy; Siddharth Garg; Ramesh Karri; Farshad Khorrami

doi:10.1109/ETS48528.2020.9131596

Anomaly Detection in Embedded Systems Using Power and Memory Side Channels

Jiho Park, Virinchi Roy Surabhi, Prashanth Krishnamurthy, Siddharth Garg, Ramesh Karri, Farshad Khorrami

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

Abstract

We propose multi-modal anomaly detection in embedded systems using time-correlated measurements of power consumption and memory accesses. Time series of power consumption of the processor and memory accesses between L2 cache and memory bus under known-good conditions are used to train one-class support vector machine (SVM) and isolation forest classifiers. These side channels have complementary anomaly detection capabilities. Experiments on a high-fidelity processor emulator show that the method accurately detects anomalies.

Original language	English (US)
Title of host publication	Proceedings - 2020 IEEE European Test Symposium, ETS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728143125
DOIs	https://doi.org/10.1109/ETS48528.2020.9131596
State	Published - May 2020
Event	2020 IEEE European Test Symposium, ETS 2020 - Tallinn, Estonia Duration: May 25 2020 → May 29 2020

Publication series

Name	Proceedings of the European Test Workshop
Volume	2020-May
ISSN (Print)	1530-1877
ISSN (Electronic)	1558-1780

Conference

Conference	2020 IEEE European Test Symposium, ETS 2020
Country/Territory	Estonia
City	Tallinn
Period	5/25/20 → 5/29/20

Keywords

Anomaly detection
cybersecurity
memory access
power consumption
support vector machine (SVM)

ASJC Scopus subject areas

Electrical and Electronic Engineering
Industrial and Manufacturing Engineering
Software

Access to Document

10.1109/ETS48528.2020.9131596

Cite this

Park, J., Surabhi, V. R., Krishnamurthy, P., Garg, S., Karri, R., & Khorrami, F. (2020). Anomaly Detection in Embedded Systems Using Power and Memory Side Channels. In Proceedings - 2020 IEEE European Test Symposium, ETS 2020 Article 9131596 (Proceedings of the European Test Workshop; Vol. 2020-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ETS48528.2020.9131596

Anomaly Detection in Embedded Systems Using Power and Memory Side Channels. / Park, Jiho; Surabhi, Virinchi Roy; Krishnamurthy, Prashanth et al.
Proceedings - 2020 IEEE European Test Symposium, ETS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9131596 (Proceedings of the European Test Workshop; Vol. 2020-May).

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

Park, J, Surabhi, VR, Krishnamurthy, P, Garg, S , Karri, R & Khorrami, F 2020, Anomaly Detection in Embedded Systems Using Power and Memory Side Channels. in Proceedings - 2020 IEEE European Test Symposium, ETS 2020., 9131596, Proceedings of the European Test Workshop, vol. 2020-May, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE European Test Symposium, ETS 2020, Tallinn, Estonia, 5/25/20. https://doi.org/10.1109/ETS48528.2020.9131596

@inproceedings{02ddb35752ff4f0790486d9b6eb094a2,

title = "Anomaly Detection in Embedded Systems Using Power and Memory Side Channels",

abstract = "We propose multi-modal anomaly detection in embedded systems using time-correlated measurements of power consumption and memory accesses. Time series of power consumption of the processor and memory accesses between L2 cache and memory bus under known-good conditions are used to train one-class support vector machine (SVM) and isolation forest classifiers. These side channels have complementary anomaly detection capabilities. Experiments on a high-fidelity processor emulator show that the method accurately detects anomalies.",

keywords = "Anomaly detection, cybersecurity, memory access, power consumption, support vector machine (SVM)",

author = "Jiho Park and Surabhi, {Virinchi Roy} and Prashanth Krishnamurthy and Siddharth Garg and Ramesh Karri and Farshad Khorrami",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE European Test Symposium, ETS 2020 ; Conference date: 25-05-2020 Through 29-05-2020",

year = "2020",

month = may,

doi = "10.1109/ETS48528.2020.9131596",

language = "English (US)",

series = "Proceedings of the European Test Workshop",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2020 IEEE European Test Symposium, ETS 2020",

}

TY - GEN

T1 - Anomaly Detection in Embedded Systems Using Power and Memory Side Channels

AU - Park, Jiho

AU - Surabhi, Virinchi Roy

AU - Krishnamurthy, Prashanth

AU - Garg, Siddharth

AU - Karri, Ramesh

AU - Khorrami, Farshad

PY - 2020/5

Y1 - 2020/5

N2 - We propose multi-modal anomaly detection in embedded systems using time-correlated measurements of power consumption and memory accesses. Time series of power consumption of the processor and memory accesses between L2 cache and memory bus under known-good conditions are used to train one-class support vector machine (SVM) and isolation forest classifiers. These side channels have complementary anomaly detection capabilities. Experiments on a high-fidelity processor emulator show that the method accurately detects anomalies.

AB - We propose multi-modal anomaly detection in embedded systems using time-correlated measurements of power consumption and memory accesses. Time series of power consumption of the processor and memory accesses between L2 cache and memory bus under known-good conditions are used to train one-class support vector machine (SVM) and isolation forest classifiers. These side channels have complementary anomaly detection capabilities. Experiments on a high-fidelity processor emulator show that the method accurately detects anomalies.

KW - Anomaly detection

KW - cybersecurity

KW - memory access

KW - power consumption

KW - support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85089143587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089143587&partnerID=8YFLogxK

U2 - 10.1109/ETS48528.2020.9131596

DO - 10.1109/ETS48528.2020.9131596

M3 - Conference contribution

AN - SCOPUS:85089143587

T3 - Proceedings of the European Test Workshop

BT - Proceedings - 2020 IEEE European Test Symposium, ETS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE European Test Symposium, ETS 2020

Y2 - 25 May 2020 through 29 May 2020

ER -

Anomaly Detection in Embedded Systems Using Power and Memory Side Channels

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this