Secure Tiny Machine Learning on Resource-Constrained IoT Devices

Yassine Maleh, Ismail Lamaakal, Khalid El MakkaouiOpenalex Unknown 2025 · DOI · OpenAlex

Abstract

The Internet of Things (IoT) has revolutionised technology by connecting billions of smart devices, with Tiny Machine Learning (TinyML) enabling machine learning on resource-constrained devices for intelligent edge operations. However, this progress brings substantial security challenges. The limited memory and processing capabilities of TinyML devices make conventional security measures ineffective, while their widespread deployment and physical accessibility increase vulnerability to attacks. This chapter offers a detailed examination of security strategies tailored for TinyML devices within IoT networks. Leveraging current research and industry standards, it addresses the unique challenges of these systems and introduces innovative security solutions. The study encompasses technical foundations, practical implementations, and real-world case studies, with a focus on smart health applications.
BibTeX
@inproceedings{maleh2025secure,
  author = {Yassine Maleh and Ismail Lamaakal and Khalid El Makkaoui},
  title = {{Secure Tiny Machine Learning on Resource-Constrained IoT Devices}},
  booktitle = {Openalex Unknown},
  year = {2025},
  doi = {10.1201/9781003544449-8},
}

Loading related content...

Figure