Book Image

Machine Learning Security Principles

By : John Paul Mueller
Book Image

Machine Learning Security Principles

By: John Paul Mueller

Overview of this book

Businesses are leveraging the power of AI to make undertakings that used to be complicated and pricy much easier, faster, and cheaper. The first part of this book will explore these processes in more depth, which will help you in understanding the role security plays in machine learning. As you progress to the second part, you’ll learn more about the environments where ML is commonly used and dive into the security threats that plague them using code, graphics, and real-world references. The next part of the book will guide you through the process of detecting hacker behaviors in the modern computing environment, where fraud takes many forms in ML, from gaining sales through fake reviews to destroying an adversary’s reputation. Once you’ve understood hacker goals and detection techniques, you’ll learn about the ramifications of deep fakes, followed by mitigation strategies. This book also takes you through best practices for embracing ethical data sourcing, which reduces the security risk associated with data. You’ll see how the simple act of removing personally identifiable information (PII) from a dataset lowers the risk of social engineering attacks. By the end of this machine learning book, you'll have an increased awareness of the various attacks and the techniques to secure your ML systems effectively.
Table of Contents (19 chapters)
1
Part 1 – Securing a Machine Learning System
5
Part 2 – Creating a Secure System Using ML
12
Part 3 – Protecting against ML-Driven Attacks
15
Part 4 – Performing ML Tasks in an Ethical Manner

Defining an environment

An environment is the sum of the interaction an object has with the world—whether it’s an application running on a network, with the network or the internet as its environment, a robot running an assembly line, with the building housing the assembly line as its environment, or a human working in an office with the real world as an environment is immaterial. An environment defines the surroundings in which an entity operates and therefore interacts with other entities. Each environment is unique but contains common elements that make it possible to secure the environment. An ML environment includes the following elements, which are used as the basis for discussion as the chapter progresses:

  • Data of any type and from any source
  • An application model
  • Ancillary code, such as libraries
  • Interfaces to third-party code such as services
  • An Application Programming Interface (API)
  • Third-party applications that interact directly...