R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors

Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique

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

Abstract

Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This paper studies the robustness of SNNs against adversarial attacks on such DVS-based systems, and proposes R-SNN, a novel methodology for robustifying SNNs through efficient DVS-noise filtering. We are the first to generate adversarial attacks on DVS signals (i.e., frames of events in the spatio-temporal domain) and to apply noise filters for DVS sensors in the quest for defending against adversarial attacks. Our results show that the noise filters effectively prevent the SNNs from being fooled. The SNNs in our experiments provide more than 90% accuracy on the DVS-Gesture and NMNIST datasets under different adversarial threat models.

Original languageEnglish (US)
Title of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6315-6321
Number of pages7
ISBN (Electronic)9781665417143
DOIs
StatePublished - 2021
Event2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021 - Prague, Czech Republic
Duration: Sep 27 2021Oct 1 2021

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
Country/TerritoryCzech Republic
CityPrague
Period9/27/2110/1/21

Keywords

  • Adversarial Attacks
  • DVS
  • DVS-Gesture
  • Deep Learning
  • Defense
  • Dynamic Vision Sensors
  • Event-Based
  • Filter
  • NMNIST
  • Neuromorphic
  • Noise
  • Perturbation
  • Robustness
  • SNNs
  • Security
  • Spiking Neural Networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors'. Together they form a unique fingerprint.

Cite this