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

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 be...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Vol. 24; no. 18; p. 5951
Main Authors: Moskalenko, Viacheslav, Kharchenko, Vyacheslav, Semenov, Serhii
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 13.09.2024
MDPI
Subjects:
Adaptation
adversarial attack
affordable resilience
Artificial intelligence
Business metrics
Comparative analysis
concept drift
dynamic deep neural networks
Edge computing
Efficiency
Embedded systems
fault injection
Fault tolerance
Methods
Neural networks
R&D
Research & development
robustness
Ukraine
adversarial attack
robustness
dynamic deep neural networks
affordable resilience
fault injection
concept drift
ISSN:1424-8220, 1424-8220
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s24185951