Analysis of Power-Oriented Fault Injection Attacks on Spiking Neural Networks

Karthikeyan Nagarajan, Junde Li, Sina Sayyah Ensan, Mohammad Nasim Imtiaz Khan, Sachhidh Kannan, Swaroop Ghosh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Spiking Neural Networks (SNN) are quickly gaining traction as a viable alternative to Deep Neural Networks (DNN). In comparison to DNNs, SNNs are more computationally powerful and provide superior en-ergy efficiency. SNNs, while exciting at first appearance, contain security-sensitive assets (e.g., neuron threshold voltage) and vulnerabilities (e.g., sensitivity of classification accuracy to neuron threshold voltage change) that adversaries can exploit. We investigate global fault injection attacks by employing external power supplies and laser-induced local power glitches to corrupt crucial training parameters such as spike amplitude and neuron's membrane threshold potential on SNNs developed using common analog neurons. We also evaluate the impact of power-based attacks on individual SNN layers for 0% (i.e., no attack) to 100% (i.e., whole layer under attack). We investigate the impact of the attacks on digit classification tasks and find that in the worst-case scenario, classification accuracy is reduced by 85.65%. We also propose defenses e.g., a robust current driver design that is immune to power-oriented attacks, improved circuit sizing of neuron components to reduce/recover the adversarial accuracy degradation at the cost of negligible area and 25% power overhead. We also present a dummy neuron-based voltage fault injection detection system with 1% power and area overhead.

Original languageEnglish (US)
Title of host publicationProceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
EditorsCristiana Bolchini, Ingrid Verbauwhede, Ioana Vatajelu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages861-866
Number of pages6
ISBN (Electronic)9783981926361
DOIs
StatePublished - 2022
Event2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 - Virtual, Online, Belgium
Duration: Mar 14 2022Mar 23 2022

Publication series

NameProceedings of the 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022

Conference

Conference2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022
Country/TerritoryBelgium
CityVirtual, Online
Period3/14/223/23/22

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software
  • Safety, Risk, Reliability and Quality
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Analysis of Power-Oriented Fault Injection Attacks on Spiking Neural Networks'. Together they form a unique fingerprint.

Cite this