As the deployment of artifical intelligence (AI) algorithms at edge devices becomes increasingly prevalent, enhancing the robustness and reliability of autonomous AI-based perception and decision systems is becoming as relevant as precision and performance, especially in applications areas considered safety-critical such as autonomous driving and aerospace. This paper delves into the robustness assessment in embedded Deep Neural Networks (DNNs), particularly focusing on the impact of parameter perturbations produced by single event upsets (SEUs) on convolutional neural networks (CNN) for image semantic segmentation. By scrutinizing the layer-by-layer and bit-by-bit sensitivity of various encoder-decoder models to soft errors, this study thoroughly investigates the vulnerability of segmentation DNNs to SEUs and evaluates the consequences of techniques like model pruning and parameter quantization on the robustness of compressed models aimed at embedded implementations. The findings offer valuable insights into the mechanisms underlying SEU-induced failures that allow for evaluating the robustness of DNNs once trained in advance. Moreover, based on the collected data, we propose a set of practical lightweight error mitigation techniques with no memory or computational cost suitable for resource-constrained deployments. The code used to perform the fault injection (FI) campaign is available at https://github.com/jonGuti13/TensorFI2 , while the code to implement proposed techniques is available at https://github.com/jonGuti13/parameterProtection .

翻译：随着人工智能算法在边缘设备上的部署日益普遍，提升基于人工智能的自主感知与决策系统的鲁棒性与可靠性正变得与精度和性能同等重要，这在自动驾驶和航空航天等被视为安全关键的应用领域尤为突出。本文深入研究了嵌入式深度神经网络的鲁棒性评估，特别聚焦于单粒子翻转导致的参数扰动对用于图像语义分割的卷积神经网络的影响。通过细致分析多种编码器-解码器模型对软错误的逐层逐比特敏感性，本研究系统探究了语义分割深度神经网络对单粒子翻转的脆弱性，并评估了模型剪枝与参数量化等面向嵌入式实现的模型压缩技术对鲁棒性的影响。研究结果为理解单粒子翻转引发故障的内在机制提供了重要见解，使得能够在训练完成后预先评估深度神经网络的鲁棒性。此外，基于收集的数据，我们提出了一套实用的轻量级错误缓解技术，这些技术无需内存或计算开销，适用于资源受限的部署环境。执行故障注入实验的代码发布于 https://github.com/jonGuti13/TensorFI2 ，而实现所提技术的代码发布于 https://github.com/jonGuti13/parameterProtection 。