| Autor: |
Moskalenko V; Department of Computer Science, Sumy State University, 116, Kharkivska Str., 40007 Sumy, Ukraine., Kharchenko V; Department of Computer Systems, Networks and Cybersecurity, National Aerospace University 'KhAI', 17, Chkalov Str., 61070 Kharkiv, Ukraine., Semenov S; Cyber Security Department, University of the National Education Commission, Ul. Podchorążych 2, 30-084 Kraków, Poland. |
| Jazyk: |
angličtina |
| Zdroj: |
Sensors (Basel, Switzerland) [Sensors (Basel)] 2024 Sep 13; Vol. 24 (18). Date of Electronic Publication: 2024 Sep 13. |
| DOI: |
10.3390/s24185951 |
| Abstrakt: |
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. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
