Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing - Use Cases and Emerging Challenges
Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing - Use Cases and Emerging Challenges
复制标题
用于网络物理、物联网和边缘计算的嵌入式机器学习 - 用例和新兴挑战
DOI：
10.1007/978-3-031-40677-5_19
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Alouani I
中科院分区：
文献类型：
--
作者：
Alouani I
与基于云的方法相比，在嵌入式系统和边缘设备中部署机器学习具有有趣的优势，特别是从功耗和环境影响的角度来看。然而，对于可信的嵌入式ML，需要解决两个主要问题；第一，对错误的健壮性：几个故障来源可能危及ML系统的完整性；无论是硬件故障，以及恶意故障注入。第二，安全性和隐私性：这包括敌意攻击和信息泄露。在本章中，我们通过对深度神经网络固有的容错能力的探索性研究来研究这些问题，并概述了嵌入式系统友好的防御对手攻击的方法。此外，我们还概述了隐私问题，并讨论了我们认为社区需要调查的公开问题。
Machine Learning deployment in Embedded Systems and Edge devices offer interesting advantages compared with the Cloud-based approaches, especially from a power consumption and environmental impact perspective. However, two principal problems need to be addressed towards trustworthy Embedded ML; first, Robustness to errors: several sources of faults can jeopardize ML systems integrity; be it hardware failures, as well as malicious fault injection. Second, Security and Privacy: this includes adversarial attacks and information leakage.In this chapter, we investigate these issues with an exploratory study on inherent fault tolerance of deep neural networks, as well as an overview on Embedded Systems-friendly defenses against adversarial attacks. Moreover, we provide an overview on privacy issues and discuss open problems we think the community needs to investigate.