Adversarial Training for Probabilistic Spiking Neural Networks

Alireza Bagheri, Osvaldo Simeone, Bipin Rajendran

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

5 Scopus citations

Abstract

Classifiers trained using conventional empirical risk minimization or maximum likelihood methods are known to suffer dramatic performance degradations when tested over examples adversarially selected based on knowledge of the clas-sifier's decision rule. Due to the prominence of Artificial Neural Networks (ANNs) as classifiers, their sensitivity to adversarial examples, as well as robust training schemes, have been recently the subject of intense investigation. In this paper, for the first time, the sensitivity of spiking neural networks (SNNs), or third-generation neural networks, to adversarial examples is studied. The study considers rate and time encoding, as well as rate and first-to-spike decoding. Furthermore, a robust training mechanism is proposed that is demonstrated to enhance the performance of SNNs under white-box attacks.

Original languageEnglish (US)
Title of host publication2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781538635124
DOIs
StatePublished - Aug 24 2018
Externally publishedYes
Event19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018 - Kalamata, Greece
Duration: Jun 25 2018Jun 28 2018

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
Volume2018-June

Other

Other19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
Country/TerritoryGreece
CityKalamata
Period6/25/186/28/18

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Keywords

  • Generalized Linear Model (GLM)
  • Spiking Neural Networks (SNNs)
  • adversarial examples
  • adversarial training

Fingerprint

Dive into the research topics of 'Adversarial Training for Probabilistic Spiking Neural Networks'. Together they form a unique fingerprint.

Cite this