Malicious loop detection using support vector machine

Zirak Allaf; Mo Adda; Alexander Gegov

doi:10.1109/INISTA.2019.8778291

Malicious loop detection using support vector machine

Zirak Allaf, Mo Adda, Alexander Gegov

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

220 Downloads (Pure)

Abstract

Existing Side-channel attack techniques, such as meltdown attacks, show that attackers can exploit the microarchitecture and OS vulnerabilities to achieve their goals. In this paper, we present the development of our real-time system for detecting side-channel attacks. Unlike previous works, our proposed detection system does not rely on synchronisation between the attackers and victims. Instead, it uses processors’ performance indicators to capture malicious Flush+Reload activities with an accuracy of up to 99%. Moreover, the detection activities can be achieved with minimum time delay in both native and cloud systems with a low overhead performance approximately less than 1% in the host system.

Original language	English
Title of host publication	2019 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	978-1-7281-1862-8
ISBN (Print)	978-1-7281-1863-5
DOIs	https://doi.org/10.1109/INISTA.2019.8778291
Publication status	Published - 29 Jul 2019
Event	IEEE INISTA 2019: International Symposium on Innovations in Intelligent Systems and Applications - Sofia, Bulgaria Duration: 3 Jul 2019 → 5 Jul 2019

Conference

Conference	IEEE INISTA 2019
Country/Territory	Bulgaria
City	Sofia
Period	3/07/19 → 5/07/19

Access to Document

10.1109/INISTA.2019.8778291

INISTA_2019_paper_46
© © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 321 KB

Cite this

@inproceedings{4048a2a5965547dfa30c7d505f93fd06,

title = "Malicious loop detection using support vector machine",

abstract = "Existing Side-channel attack techniques, such as meltdown attacks, show that attackers can exploit the microarchitecture and OS vulnerabilities to achieve their goals. In this paper, we present the development of our real-time system for detecting side-channel attacks. Unlike previous works, our proposed detection system does not rely on synchronisation between the attackers and victims. Instead, it uses processors{\textquoteright} performance indicators to capture malicious Flush+Reload activities with an accuracy of up to 99%. Moreover, the detection activities can be achieved with minimum time delay in both native and cloud systems with a low overhead performance approximately less than 1% in the host system.",

author = "Zirak Allaf and Mo Adda and Alexander Gegov",

year = "2019",

month = jul,

day = "29",

doi = "10.1109/INISTA.2019.8778291",

language = "English",

isbn = "978-1-7281-1863-5",

booktitle = "2019 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings",

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

address = "United States",

note = "IEEE INISTA 2019 : International Symposium on Innovations in Intelligent Systems and Applications ; Conference date: 03-07-2019 Through 05-07-2019",

}

TY - GEN

T1 - Malicious loop detection using support vector machine

AU - Allaf, Zirak

AU - Adda, Mo

AU - Gegov, Alexander

PY - 2019/7/29

Y1 - 2019/7/29

N2 - Existing Side-channel attack techniques, such as meltdown attacks, show that attackers can exploit the microarchitecture and OS vulnerabilities to achieve their goals. In this paper, we present the development of our real-time system for detecting side-channel attacks. Unlike previous works, our proposed detection system does not rely on synchronisation between the attackers and victims. Instead, it uses processors’ performance indicators to capture malicious Flush+Reload activities with an accuracy of up to 99%. Moreover, the detection activities can be achieved with minimum time delay in both native and cloud systems with a low overhead performance approximately less than 1% in the host system.

AB - Existing Side-channel attack techniques, such as meltdown attacks, show that attackers can exploit the microarchitecture and OS vulnerabilities to achieve their goals. In this paper, we present the development of our real-time system for detecting side-channel attacks. Unlike previous works, our proposed detection system does not rely on synchronisation between the attackers and victims. Instead, it uses processors’ performance indicators to capture malicious Flush+Reload activities with an accuracy of up to 99%. Moreover, the detection activities can be achieved with minimum time delay in both native and cloud systems with a low overhead performance approximately less than 1% in the host system.

U2 - 10.1109/INISTA.2019.8778291

DO - 10.1109/INISTA.2019.8778291

M3 - Conference contribution

SN - 978-1-7281-1863-5

BT - 2019 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE INISTA 2019

Y2 - 3 July 2019 through 5 July 2019

ER -

Malicious loop detection using support vector machine

Abstract

Conference

Access to Document

Fingerprint

Cite this