Deterministic and Statistical Strategies to Protect ANNs against Fault Injection Attacks

T.C. Köylü*, Cezar Reinbrecht, S. Hamdioui, M. Taouil

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

1 Citation (Scopus)
20 Downloads (Pure)

Abstract

Artificial neural networks are currently used for many tasks, including safety critical ones such as automated driving. Hence, it is very important to protect them against faults and fault attacks. In this work, we propose two fault injection attack detection mechanisms: one based on using output labels for a reference input, and the other on the activations of neurons. First, we calibrate our detectors during normal conditions. Thereafter, we verify them to maximize fault detection performance. To prove the effectiveness of our solution, we consider highly employed neural networks (AlexNet, GoogleNet, and VGG) with their associated dataset ImageNet. Our results show that for both detectors we are able to obtain a high rate of coverage against faults, typically above 96%. Moreover, the hardware and software implementations of our detector indicate an extremely low area and time overhead.
Original languageEnglish
Title of host publication2021 18th International Conference on Privacy, Security and Trust (PST)
Place of PublicationPiscataway
PublisherIEEE
Pages1-10
Number of pages10
ISBN (Electronic)978-1-6654-0184-5
ISBN (Print)978-1-6654-0185-2
DOIs
Publication statusPublished - 2021
Event18th Annual International Conference on Privacy, Security and Trust (PST2021) - Virtual at Auckland, New Zealand
Duration: 13 Dec 202115 Dec 2021
Conference number: 18

Publication series

Name2021 18th International Conference on Privacy, Security and Trust, PST 2021

Conference

Conference18th Annual International Conference on Privacy, Security and Trust (PST2021)
Abbreviated titlePST2021
Country/TerritoryNew Zealand
CityVirtual at Auckland
Period13/12/2115/12/21

Keywords

  • Fault Injection
  • Countermeasures
  • Artificial neural networks
  • Machine learning

Fingerprint

Dive into the research topics of 'Deterministic and Statistical Strategies to Protect ANNs against Fault Injection Attacks'. Together they form a unique fingerprint.

Cite this