Nonideality-aware training makes memristive networks more robust to adversarial attacks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Joksas, Dovydas, Muñoz-González, Luis, Lupu, Emil, Mehonic, Adnan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917789742137344
author Joksas, Dovydas
Muñoz-González, Luis
Lupu, Emil
Mehonic, Adnan
author_facet Joksas, Dovydas
Muñoz-González, Luis
Lupu, Emil
Mehonic, Adnan
contents Neural networks are now deployed in a wide number of areas from object classification to natural language systems. Implementations using analog devices like memristors promise better power efficiency, potentially bringing these applications to a greater number of environments. However, such systems suffer from more frequent device faults and overall, their exposure to adversarial attacks has not been studied extensively. In this work, we investigate how nonideality-aware training - a common technique to deal with physical nonidealities - affects adversarial robustness. We find that adversarial robustness is significantly improved, even with limited knowledge of what nonidealities will be encountered during test time.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nonideality-aware training makes memristive networks more robust to adversarial attacks
Joksas, Dovydas
Muñoz-González, Luis
Lupu, Emil
Mehonic, Adnan
Emerging Technologies
Cryptography and Security
Machine Learning
Neural networks are now deployed in a wide number of areas from object classification to natural language systems. Implementations using analog devices like memristors promise better power efficiency, potentially bringing these applications to a greater number of environments. However, such systems suffer from more frequent device faults and overall, their exposure to adversarial attacks has not been studied extensively. In this work, we investigate how nonideality-aware training - a common technique to deal with physical nonidealities - affects adversarial robustness. We find that adversarial robustness is significantly improved, even with limited knowledge of what nonidealities will be encountered during test time.
title Nonideality-aware training makes memristive networks more robust to adversarial attacks
topic Emerging Technologies
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2409.19671