10 Using Machine Learning for Protecting the Security and Privacy of Internet of Things (IoT) Systems

Melody Moh and Robinson Raju

10.1 Introduction

Today, IoT devices are ubiquitous and have pervaded almost every sphere of our lives, ushering an era of smart things:

  • Smart homes have appliances, lights, and thermostat connected to the Internet [1].
  • Smart medical appliances not only monitor remotely but also administer medicines timely [2].
  • Smart bridges have sensors to monitor loads [3].
  • Smart power grids detect disruptions and manage distribution of power [4].
  • Smart machinery in industries have embedded sensors in heavy machinery to increase worker safety and improve automation [5].

To get a better understanding of the scale of IoT, here are some numbers for review:

  • In 2008, the number of devices connected to the Internet surpassed the world population of approximately 6.7 billion people.
  • In 2015, approximately 1.4 billion smartphones were shipped by manufacturers.
  • By 2020, the prediction is that there will be 6.1 billion smartphone users and an anticipated 50 billion things connected to the Internet [6].
  • By 2027, the expectation is that there will be 27 billion machine‐to‐machine connections in the industrial sector.

Now, if the focus shifts to the amount of data that gets generated, one gets a glimpse of the dawn of the zettabyte era [7]. To put a zettabyte into perspective, 36,000 years of high‐definition television video would be the equivalent of one zettabyte. ...

Get Fog and Edge Computing now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.