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.
展开▼
机译：人工智能技术在资源受限、安全关键的嵌入式系统中越来越普遍。有许多方法可以增强 AI 系统对破坏性影响的弹性。然而，当资源有限时，确保具有成本效益的弹性变得至关重要。在测试期间减少 AI 系统资源消耗的一种有前途的方法涉及应用动态神经网络的概念和方法。然而，动态神经网络对各种干扰的弹性仍未得到充分探索。本文提出了一种模型架构和训练方法，该方法集成了动态神经网络，重点关注弹性。与传统训练方法相比，所提出的方法使卷积网络的弹性提高了 24%，在故障注入下视觉转换器的弹性提高了 19.7%。此外，它还使卷积网络 ResNet-110 的弹性提高了 16.9%，视觉转换器 DeiT-S 在对抗性攻击下的弹性提高了 21.6%，同时节省了 30% 以上的计算资源。对神经网络模型进行元训练后，对任务变化的弹性平均提高了 22%，同时实现了相同级别的资源节省。
展开▼
