EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Dovydas Joksas, Luis Muñoz-González, Emil Lupu, Adnan Mehonic

APL Machine Learning · 01.03.2025 · 3 (1)

DOI: 10.1063/5.0241202 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Machine Learning, online erschienen am 11.02.2025. Verfasst von Dovydas Joksas und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Royal Academy of Engineering, EPSRC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural networks are now deployed in a wide number of areas, from object classification to natural language systems. Implementations using analog devices such as 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.

Förderung

  • Royal Academy of Engineering
  • EPSRC

Zitieren

APA

Joksas, D., Muñoz-González, L., Lupu, E., & Mehonic, A. (2025). Nonideality-aware training makes memristive networks more robust to adversarial attacks. APL Machine Learning, 3(1). https://doi.org/10.1063/5.0241202

Vancouver

Joksas D, Muñoz-González L, Lupu E, Mehonic A. Nonideality-aware training makes memristive networks more robust to adversarial attacks. APL Machine Learning. 2025;3(1). doi:10.1063/5.0241202

BibTeX
@article{Joksas2025,
  author = {Joksas, Dovydas and Muñoz-González, Luis and Lupu, Emil and Mehonic, Adnan},
  title = {Nonideality-aware training makes memristive networks more robust to adversarial attacks},
  journal = {APL Machine Learning},
  year = {2025},
  volume = {3},
  number = {1},
  doi = {10.1063/5.0241202}
}
Kostenlos starten →