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)
Part 1 – Securing a Machine Learning System
Part 2 – Creating a Secure System Using ML
Part 3 – Protecting against ML-Driven Attacks
Part 4 – Performing ML Tasks in an Ethical Manner

Defining data source awareness

The internet makes it incredibly easy to locate many common kinds of dataset. There are so many datasets available for some purposes that sometimes it’s hard to choose based on the content of the dataset alone. However, content isn’t the only consideration. It’s also important to consider the third party that collected it. In some cases, datasets are extremely biased or have special requirements that make them inappropriate to use for many kinds of analysis. Even if you were to ignore the issues with the dataset, the experimentation you perform with it would yield less-than-useful results.

Validating user permissions

Part of data source awareness is to ensure that people using the dataset actually have the need and credentials to use it. This is especially true with datasets that deal with sensitive or confidential materials, or datasets that are controlled by government regulation, such as medical datasets that must follow...