The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural networks (DNNs) and spiking neural networks (SNNs), that offer state-of-the-art results on resource-constrained edge devices is challenging due to the stringent memory and power/energy constraints. Moreover, these systems are required to maintain correct functionality under diverse security and reliability threats. This paper first discusses existing approaches to address energy efficiency, reliability, and security issues at different system layers, i.e., hardware (HW) and software (SW). Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation. To address reliability threats (like permanent and transient faults), we highlight cost-effective mitigation techniques, like fault-aware training and mapping. Moreover, we briefly discuss effective detection and protection techniques to address security threats (like model and data corruption). Towards the end, we discuss how these techniques can be combined in an integrated cross-layer framework for realizing robust and energy-efficient Edge AI systems.
翻译:由于严格的记忆和电力/能源限制,安全和隐私方面的关切以及需要定期处理的数据数量,使处理工作推向了计算系统的边缘。部署先进的神经网络(NN),例如深神经网络(DNN)和喷射神经网络(SNN),这些网络在资源限制的边缘装置上提供最先进的结果,由于严格的记忆和电力/能源限制,这些系统需要保持不同安全和可靠性威胁下的正确功能。本文件首先讨论了在不同系统层,如硬件和软件(SW)解决能源效率、可靠性和安全问题的现有办法。之后,我们讨论如何通过HW/SW级优化,如裁剪、裁量和近似,进一步改进AI系统的性能(latenity)和能效。为了应对可靠性威胁(如永久和短暂的错误),我们强调成本效益高的缓解技术,例如错误意识培训和绘图。此外,我们简要地讨论了如何通过有效的检测和保护技术(如模型和高能效综合数据框架)来共同应对安全威胁(实现AI级综合能源腐败)。