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

Adding ML to the mix

Once you get past the traditional defenses, you can use ML to implement Network Traffic Analytics (NTA) as part of an IDS, as shown in Figure 5.2. Most ML strategies are based on some sort of anomaly detection. For example, it’s popular to use convolutional auto-encoders for network intrusion detection. A few early products still in the research stage, such as nPrintML, discussed in New Directions in Automated Traffic Analysis at, have also made an appearance. Here are just a few of the ways in which you can use ML to augment traditional security layers:

  • Perform regression analysis to determine whether certain packets are somehow flawed compared to normal packets from a given source. In other words, you’re not dealing with absolutes but, rather, determining what is normal from a particular sender. Anything outside the normal pattern is suspect.
  • Rely on classification to detect whether incoming data matches particular...