Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing

Sanjeev Tannirkulam Chandrasekaran; Abraham Peedikayil Kuruvila; Kanad Basu; Arindam Sanyal

doi:10.1109/TCSII.2021.3102526

Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing

Sanjeev Tannirkulam Chandrasekaran, Abraham Peedikayil Kuruvila, Kanad Basu, Arindam Sanyal

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

5 Scopus citations

Abstract

In this work we demonstrate a novel CMOS reservoir computer (RC) prototype in 65nm CMOS that is capable of detecting Malware and micro-architectural attacks in realtime utilizing hardware performance counter (HPC) traces. A 65nm test chip achieves 96.8% and 96.5% accuracy when classifying Malware and micro-architectural attacks respectively, while achieving better classification performance than digital machine learning models and with lower energy consumption. The on-chip classifier consumes 38.2μW from a 1.2V supply while running at 40kHz.

Original language	English (US)
Pages (from-to)	349-353
Number of pages	5
Journal	IEEE Transactions on Circuits and Systems II: Express Briefs
Volume	69
Issue number	2
DOIs	https://doi.org/10.1109/TCSII.2021.3102526
State	Published - Feb 1 2022
Externally published	Yes

Keywords

Hardware
Malware
Neurons
Perturbation methods
Program processors
Reservoirs
Resists

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/TCSII.2021.3102526

Cite this

Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing. / Chandrasekaran, Sanjeev Tannirkulam; Kuruvila, Abraham Peedikayil; Basu, Kanad et al.
In: IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 69, No. 2, 01.02.2022, p. 349-353.

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

@article{3a36b62b5c8e4b31b46c37c7dcc54158,

title = "Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing",

abstract = "In this work we demonstrate a novel CMOS reservoir computer (RC) prototype in 65nm CMOS that is capable of detecting Malware and micro-architectural attacks in realtime utilizing hardware performance counter (HPC) traces. A 65nm test chip achieves 96.8% and 96.5% accuracy when classifying Malware and micro-architectural attacks respectively, while achieving better classification performance than digital machine learning models and with lower energy consumption. The on-chip classifier consumes 38.2μW from a 1.2V supply while running at 40kHz.",

keywords = "Hardware, Malware, Neurons, Perturbation methods, Program processors, Reservoirs, Resists",

author = "Chandrasekaran, {Sanjeev Tannirkulam} and Kuruvila, {Abraham Peedikayil} and Kanad Basu and Arindam Sanyal",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.",

year = "2022",

month = feb,

day = "1",

doi = "10.1109/TCSII.2021.3102526",

language = "English (US)",

volume = "69",

pages = "349--353",

journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",

issn = "1549-7747",

number = "2",

}

TY - JOUR

T1 - Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing

AU - Chandrasekaran, Sanjeev Tannirkulam

AU - Kuruvila, Abraham Peedikayil

AU - Basu, Kanad

AU - Sanyal, Arindam

PY - 2022/2/1

Y1 - 2022/2/1

N2 - In this work we demonstrate a novel CMOS reservoir computer (RC) prototype in 65nm CMOS that is capable of detecting Malware and micro-architectural attacks in realtime utilizing hardware performance counter (HPC) traces. A 65nm test chip achieves 96.8% and 96.5% accuracy when classifying Malware and micro-architectural attacks respectively, while achieving better classification performance than digital machine learning models and with lower energy consumption. The on-chip classifier consumes 38.2μW from a 1.2V supply while running at 40kHz.

AB - In this work we demonstrate a novel CMOS reservoir computer (RC) prototype in 65nm CMOS that is capable of detecting Malware and micro-architectural attacks in realtime utilizing hardware performance counter (HPC) traces. A 65nm test chip achieves 96.8% and 96.5% accuracy when classifying Malware and micro-architectural attacks respectively, while achieving better classification performance than digital machine learning models and with lower energy consumption. The on-chip classifier consumes 38.2μW from a 1.2V supply while running at 40kHz.

KW - Hardware

KW - Malware

KW - Neurons

KW - Perturbation methods

KW - Program processors

KW - Reservoirs

KW - Resists

UR - http://www.scopus.com/inward/record.url?scp=85112670312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85112670312&partnerID=8YFLogxK

U2 - 10.1109/TCSII.2021.3102526

DO - 10.1109/TCSII.2021.3102526

M3 - Article

AN - SCOPUS:85112670312

SN - 1549-7747

VL - 69

SP - 349

EP - 353

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

IS - 2

ER -

Real-Time Hardware-Based Malware and Micro-Architectural Attack Detection Utilizing CMOS Reservoir Computing

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this