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

Developing predictive defenses

Being able to predict the future is something that everyone who is involved with security would like to have. The use of ML to help predict things such as network attacks is an ongoing venture, but there aren’t any commercial examples of such technology to date, and usable examples are also hard to find. However, it’s possible to postulate what a commercial offering might look like and start doing some experimenting of your own, as described in the sections that follow.

Defining what is available today

What you see most often today are explorations into predictive software based on new Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Multilayer Perceptron (MLP) models, which are described in articles such as CyberSecurity Attack Prediction: A Deep Learning Approach at and A deep learning framework for predicting cyber attacks rates at