On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning

Ihsen Alouani

doi:10.1007/978-3-031-40677-5_19

On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning

Ihsen Alouani

School of Electronics, Electrical Engineering and Computer Science

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

1 Citation (Scopus)

2 Downloads (Pure)

Abstract

Machine Learning deployment in Embedded Systems and Edge devices offer interesting advantages compared with the Cloud-based approaches, especially from a power consumption and environmental impact perspective. However, two principal problems need to be addressed towards trustworthy Embedded ML; first, Robustness to errors: several sources of faults can jeopardize ML systems integrity; be it hardware failures, as well as malicious fault injection. Second, Security and Privacy: this includes adversarial attacks and information leakage.

Original language	English
Title of host publication	Embedded machine learning for cyber-physical, IoT, and edge computing: use cases and emerging challenges
Editors	Sudeep Pasricha, Muhammad Shafique
Place of Publication	Cham
Publisher	Springer Nature Switzerland
Pages	497-517
Number of pages	21
ISBN (Electronic)	9783031406775
ISBN (Print)	9783031406768
DOIs	https://doi.org/10.1007/978-3-031-40677-5_19
Publication status	Published - 07 Oct 2023

Access to Document

10.1007/978-3-031-40677-5_19Licence: Unspecified

On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning
Copyright 2023 Springer This work is made available online in accordance with the publisher’s policies. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.9 MBLicence: Unspecified

Cite this

@inbook{b54623fd43b04ee4b24a392cbfffd010,

title = "On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning",

abstract = "Machine Learning deployment in Embedded Systems and Edge devices offer interesting advantages compared with the Cloud-based approaches, especially from a power consumption and environmental impact perspective. However, two principal problems need to be addressed towards trustworthy Embedded ML; first, Robustness to errors: several sources of faults can jeopardize ML systems integrity; be it hardware failures, as well as malicious fault injection. Second, Security and Privacy: this includes adversarial attacks and information leakage.",

author = "Ihsen Alouani",

year = "2023",

month = oct,

day = "7",

doi = "10.1007/978-3-031-40677-5\_19",

language = "English",

isbn = "9783031406768",

pages = "497--517",

editor = "Sudeep Pasricha and Muhammad Shafique",

booktitle = "Embedded machine learning for cyber-physical, IoT, and edge computing: use cases and emerging challenges",

publisher = "Springer Nature Switzerland",

address = "Switzerland",

}

On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning. / Alouani, Ihsen.
Embedded machine learning for cyber-physical, IoT, and edge computing: use cases and emerging challenges. ed. / Sudeep Pasricha; Muhammad Shafique. Cham: Springer Nature Switzerland, 2023. p. 497-517.

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

TY - CHAP

T1 - On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning

AU - Alouani, Ihsen

PY - 2023/10/7

Y1 - 2023/10/7

N2 - Machine Learning deployment in Embedded Systems and Edge devices offer interesting advantages compared with the Cloud-based approaches, especially from a power consumption and environmental impact perspective. However, two principal problems need to be addressed towards trustworthy Embedded ML; first, Robustness to errors: several sources of faults can jeopardize ML systems integrity; be it hardware failures, as well as malicious fault injection. Second, Security and Privacy: this includes adversarial attacks and information leakage.

AB - Machine Learning deployment in Embedded Systems and Edge devices offer interesting advantages compared with the Cloud-based approaches, especially from a power consumption and environmental impact perspective. However, two principal problems need to be addressed towards trustworthy Embedded ML; first, Robustness to errors: several sources of faults can jeopardize ML systems integrity; be it hardware failures, as well as malicious fault injection. Second, Security and Privacy: this includes adversarial attacks and information leakage.

U2 - 10.1007/978-3-031-40677-5_19

DO - 10.1007/978-3-031-40677-5_19

M3 - Chapter

SN - 9783031406768

SP - 497

EP - 517

BT - Embedded machine learning for cyber-physical, IoT, and edge computing: use cases and emerging challenges

A2 - Pasricha, Sudeep

A2 - Shafique, Muhammad

PB - Springer Nature Switzerland

CY - Cham

ER -

On the challenge of hardware errors, adversarial attacks and privacy leakage for embedded machine learning

Abstract

Access to Document

Fingerprint

Cite this