NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

Valerio Venceslai; Alberto Marchisio; Ihsen Alouani; Maurizio Martina; Muhammad Shafique

doi:10.1109/IJCNN48605.2020.9207351

NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

Valerio Venceslai, Alberto Marchisio, Ihsen Alouani, Maurizio Martina, Muhammad Shafique

Electrical Engineering

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

Abstract

Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization, and energy-efficiency challenges in machine-learning systems. While these systems are going mainstream, they have inherent security and reliability issues. In this paper, we propose NeuroAttack, a cross-layer attack that threatens the SNNs integrity by exploiting low-level reliability issues through a high-level attack. Particularly, we trigger a fault-injection based sneaky hardware backdoor through a carefully crafted adversarial input noise. Our results on Deep Neural Networks (DNNs) and SNNs show a serious integrity threat to state-of-the art machine-learning techniques.

Original language	English (US)
Title of host publication	2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728169262
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9207351
State	Published - Jul 2020
Event	2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom Duration: Jul 19 2020 → Jul 24 2020

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Conference

Conference	2020 International Joint Conference on Neural Networks, IJCNN 2020
Country/Territory	United Kingdom
City	Virtual, Glasgow
Period	7/19/20 → 7/24/20

Keywords

Adversarial Attacks
Cross-Layer
Deep Neural Networks
DNN
Fault-Injection Attacks
Machine Learning
Reliability
Resilience
Security
SNN
Spiking Neural Networks

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN48605.2020.9207351

Cite this

Venceslai, V., Marchisio, A., Alouani, I., Martina, M., & Shafique, M. (2020). NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. In 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings Article 9207351 (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN48605.2020.9207351

NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. / Venceslai, Valerio; Marchisio, Alberto; Alouani, Ihsen et al.
2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9207351 (Proceedings of the International Joint Conference on Neural Networks).

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

Venceslai, V, Marchisio, A, Alouani, I, Martina, M & Shafique, M 2020, NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. in 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings., 9207351, Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., 2020 International Joint Conference on Neural Networks, IJCNN 2020, Virtual, Glasgow, United Kingdom, 7/19/20. https://doi.org/10.1109/IJCNN48605.2020.9207351

Venceslai V, Marchisio A, Alouani I, Martina M, Shafique M. NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. In 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9207351. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN48605.2020.9207351

Venceslai, Valerio ; Marchisio, Alberto ; Alouani, Ihsen et al. / NeuroAttack : Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips. 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (Proceedings of the International Joint Conference on Neural Networks).

@inproceedings{ccef7bdd959a44b9bdf6a6ef40da7cd0,

title = "NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips",

abstract = "Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization, and energy-efficiency challenges in machine-learning systems. While these systems are going mainstream, they have inherent security and reliability issues. In this paper, we propose NeuroAttack, a cross-layer attack that threatens the SNNs integrity by exploiting low-level reliability issues through a high-level attack. Particularly, we trigger a fault-injection based sneaky hardware backdoor through a carefully crafted adversarial input noise. Our results on Deep Neural Networks (DNNs) and SNNs show a serious integrity threat to state-of-the art machine-learning techniques.",

keywords = "Adversarial Attacks, Cross-Layer, Deep Neural Networks, DNN, Fault-Injection Attacks, Machine Learning, Reliability, Resilience, Security, SNN, Spiking Neural Networks",

author = "Valerio Venceslai and Alberto Marchisio and Ihsen Alouani and Maurizio Martina and Muhammad Shafique",

note = "Funding Information: This work has been partially supported by the Doctoral College Resilient Embedded Systems which is run jointly by TU Wien{\textquoteright}s Faculty of Informatics and FH-Technikum Wien. Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

year = "2020",

month = jul,

doi = "10.1109/IJCNN48605.2020.9207351",

language = "English (US)",

series = "Proceedings of the International Joint Conference on Neural Networks",

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

booktitle = "2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings",

}

TY - GEN

T1 - NeuroAttack

T2 - 2020 International Joint Conference on Neural Networks, IJCNN 2020

AU - Venceslai, Valerio

AU - Marchisio, Alberto

AU - Alouani, Ihsen

AU - Martina, Maurizio

AU - Shafique, Muhammad

N1 - Funding Information: This work has been partially supported by the Doctoral College Resilient Embedded Systems which is run jointly by TU Wien’s Faculty of Informatics and FH-Technikum Wien. Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/7

Y1 - 2020/7

N2 - Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization, and energy-efficiency challenges in machine-learning systems. While these systems are going mainstream, they have inherent security and reliability issues. In this paper, we propose NeuroAttack, a cross-layer attack that threatens the SNNs integrity by exploiting low-level reliability issues through a high-level attack. Particularly, we trigger a fault-injection based sneaky hardware backdoor through a carefully crafted adversarial input noise. Our results on Deep Neural Networks (DNNs) and SNNs show a serious integrity threat to state-of-the art machine-learning techniques.

AB - Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization, and energy-efficiency challenges in machine-learning systems. While these systems are going mainstream, they have inherent security and reliability issues. In this paper, we propose NeuroAttack, a cross-layer attack that threatens the SNNs integrity by exploiting low-level reliability issues through a high-level attack. Particularly, we trigger a fault-injection based sneaky hardware backdoor through a carefully crafted adversarial input noise. Our results on Deep Neural Networks (DNNs) and SNNs show a serious integrity threat to state-of-the art machine-learning techniques.

KW - Adversarial Attacks

KW - Cross-Layer

KW - Deep Neural Networks

KW - DNN

KW - Fault-Injection Attacks

KW - Machine Learning

KW - Reliability

KW - Resilience

KW - Security

KW - SNN

KW - Spiking Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85093821385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85093821385&partnerID=8YFLogxK

U2 - 10.1109/IJCNN48605.2020.9207351

DO - 10.1109/IJCNN48605.2020.9207351

M3 - Conference contribution

AN - SCOPUS:85093821385

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 19 July 2020 through 24 July 2020

ER -

NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this