EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Model and Method for Providing Resilience to Resource-Constrained AI-System

Viacheslav Moskalenko iD, Vyacheslav Kharchenko iD, Serhii Semenov iD

Sensors · 13.09.2024 · 24 (18) · 5951

DOI: 10.3390/s24185951 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.09.2024. Verfasst von Viacheslav Moskalenko und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Sumy State University, 116, Kharkivska Str., 40007 Sumy, Ukraine. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence technologies are becoming increasingly prevalent in resource-constrained, safety-critical embedded systems. Numerous methods exist to enhance the resilience of AI systems against disruptive influences. However, when resources are limited, ensuring cost-effective resilience becomes crucial. A promising approach for reducing the resource consumption of AI systems during test-time involves applying the concepts and methods of dynamic neural networks. Nevertheless, the resilience of dynamic neural networks against various disturbances remains underexplored. This paper proposes a model architecture and training method that integrate dynamic neural networks with a focus on resilience. Compared to conventional training methods, the proposed approach yields a 24% increase in the resilience of convolutional networks and a 19.7% increase in the resilience of visual transformers under fault injections. Additionally, it results in a 16.9% increase in the resilience of convolutional network ResNet-110 and a 21.6% increase in the resilience of visual transformer DeiT-S under adversarial attacks, while saving more than 30% of computational resources. Meta-training the neural network model improves resilience to task changes by an average of 22%, while achieving the same level of resource savings.

Schlagwörter

Stichwörter der Autor:innen

adversarial attackaffordable resilienceconcept driftdynamic deep neural networksfault injectionrobustness

Autor:innen und Institutionen

  • Department of Computer Science, Sumy State University, 116, Kharkivska Str., 40007 Sumy, Ukraine.
  • Department of Computer Systems, Networks and Cybersecurity, National Aerospace University "KhAI", 17, Chkalov Str., 61070 Kharkiv, Ukraine.
  • Cyber Security Department, University of the National Education Commission, Ul. Podchorążych 2, 30-084 Kraków, Poland.

ORCID-Profile: Viacheslav Moskalenko, Vyacheslav Kharchenko, Serhii Semenov

Zitieren

APA

Moskalenko, V., Kharchenko, V., & Semenov, S. (2024). Model and Method for Providing Resilience to Resource-Constrained AI-System. Sensors, 24(18), 5951. https://doi.org/10.3390/s24185951

Vancouver

Moskalenko V, Kharchenko V, Semenov S. Model and Method for Providing Resilience to Resource-Constrained AI-System. Sensors. 2024;24(18):5951. doi:10.3390/s24185951

BibTeX
@article{Moskalenko2024,
  author = {Moskalenko, Viacheslav and Kharchenko, Vyacheslav and Semenov, Serhii},
  title = {Model and Method for Providing Resilience to Resource-Constrained AI-System},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {18},
  pages = {5951},
  doi = {10.3390/s24185951}
}
Kostenlos starten →