Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Machine Learning Security Principles

You're reading from   Machine Learning Security Principles Keep data, networks, users, and applications safe from prying eyes

Arrow left icon
Product type Paperback
Published in Dec 2022
Publisher Packt
ISBN-13 9781804618851
Length 450 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
John Paul Mueller John Paul Mueller
Author Profile Icon John Paul Mueller
John Paul Mueller
Arrow right icon
View More author details
Toc

Table of Contents (19) Chapters Close

Preface 1. Part 1 – Securing a Machine Learning System
2. Chapter 1: Defining Machine Learning Security FREE CHAPTER 3. Chapter 2: Mitigating Risk at Training by Validating and Maintaining Datasets 4. Chapter 3: Mitigating Inference Risk by Avoiding Adversarial Machine Learning Attacks 5. Part 2 – Creating a Secure System Using ML
6. Chapter 4: Considering the Threat Environment 7. Chapter 5: Keeping Your Network Clean 8. Chapter 6: Detecting and Analyzing Anomalies 9. Chapter 7: Dealing with Malware 10. Chapter 8: Locating Potential Fraud 11. Chapter 9: Defending against Hackers 12. Part 3 – Protecting against ML-Driven Attacks
13. Chapter 10: Considering the Ramifications of Deepfakes 14. Chapter 11: Leveraging Machine Learning for Hacking 15. Part 4 – Performing ML Tasks in an Ethical Manner
16. Chapter 12: Embracing and Incorporating Ethical Behavior 17. Index 18. Other Books You May Enjoy

Addressing fairness concerns

The first step in solving a problem is to know the problem exists. Right now, most people who create models have no idea that a problem exists. This lack of knowledge and understanding is the reason that models such as those used in the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software fail on a grand scale. If the software had been vetted with some type of fairness indicator, then there is a higher likelihood that it would have produced a fair result. The following sections look at methods of working with fairness indicators that make it possible to produce models that output a fairer result.

Is a completely fair result possible?

It isn’t actually possible to create a completely fair result today. There is a paradox involved. Either a model can treat groups fairly or it can treat individuals fairly. You can find a wealth of white papers on the topic, such as On the Apparent Conflict Between Individual and...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image