Adversarial machine learning in IoT from an insider point of view
Adversarial machine learning in IoT from an insider point of view
复制标题
DOI：
10.1016/j.jisa.2022.103341
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Fatimah Aloraini;Amir Javed;Omer F. Rana;Pete Burnap
中科院分区：
文献类型：
--
作者：
Fatimah Aloraini;Amir Javed;Omer F. Rana;Pete Burnap
随着各种应用的快速发展和重大成功，机器学习已被认为是物联网生态系统的重要组成部分。然而，机器学习模型最近很容易受到精心设计的扰动，即所谓的对抗性攻击。一个有能力的内部对手可以在训练或测试阶段颠覆机器学习模型，导致它们的行为不同。机器学习对对抗性攻击的脆弱性成为重大风险之一。因此，需要保护机器学习模型，使其能够在恶意内幕案件中安全采用。本文从内部对手的角度回顾和组织了物联网文献中提出的对抗性攻击和防御的知识体系。我们提出了一种对抗性方法的分类法，以对抗内部人员可以利用的机器学习模型。在分类下，我们讨论了这些方法如何应用于现实生活中的物联网应用程序。最后，我们探索对抗性攻击的防御方法。我们相信这可以全面概述分散的研究工作，以提高对现有内部威胁格局的认识，并鼓励其他人保护机器学习模型免受物联网生态系统中的内部威胁。
With the rapid progress and significant successes in various applications, machine learning has been considered a crucial component in the Internet of Things ecosystem. However, machine learning models have recently been vulnerable to carefully crafted perturbations, so-called adversarial attacks. A capable insider adversary can subvert the machine learning model at either the training or testing phase, causing them to behave differently. The vulnerability of machine learning to adversarial attacks becomes one of the significant risks. Therefore, there is a need to secure machine learning models enabling the safe adoption in malicious insider cases. This paper reviews and organizes the body of knowledge in adversarial attacks and defense presented in IoT literature from an insider adversary point of view. We proposed a taxonomy of adversarial methods against machine learning models that an insider can exploit. Under the taxonomy, we discuss how these methods can be applied in real-life IoT applications. Finally, we explore defensive methods against adversarial attacks. We believe this can draw a comprehensive overview of the scattered research works to raise awareness of the existing insider threats landscape and encourages others to safeguard machine learning models against insider threats in the IoT ecosystem.