Jump to ratings and reviews
Rate this book

Machine Learning and Security: Protecting Systems with Data and Algorithms

Rate this book
Can machine learning techniques solve our computer security problems and finally put an end to the cat-and-mouse game between attackers and defenders? Or is this hope merely hype? Now you can dive into the science and answer this question for yourself. With this practical guide, you'll explore ways to apply machine learning to security issues such as intrusion detection, malware classification, and network analysis.

Machine learning and security specialists Clarence Chio and David Freeman provide a framework for discussing the marriage of these two fields, as well as a toolkit of machine-learning algorithms that you can apply to an array of security problems. This book is ideal for security engineers and data scientists alike.

Learn how machine learning has contributed to the success of modern spam filters
Quickly detect anomalies, including breaches, fraud, and impending system failure
Conduct malware analysis by extracting useful information from computer binaries
Uncover attackers within the network by finding patterns inside datasets
Examine how attackers exploit consumer-facing websites and app functionality
Translate your machine learning algorithms from the lab to production
Understand the threat attackers pose to machine learning solutions

386 pages, Paperback

Published February 27, 2018

Loading interface...
Loading interface...

About the author

Clarence Chio

1 book1 follower

Ratings & Reviews

What do you think?
Rate this book

Friends & Following

Create a free account to discover what your friends think of this book!

Community Reviews

5 stars
6 (21%)
4 stars
8 (28%)
3 stars
11 (39%)
2 stars
2 (7%)
1 star
1 (3%)
Displaying 1 - 6 of 6 reviews
Profile Image for Ben Rothke.
230 reviews23 followers
July 15, 2018
Machine learning and security are all the rage. With the RSA Conference a little more than 2 weeks away, there will be plenty of firms on the expo floor touting their security solutions based on AI, deep learning, and machine learning.

In Machine Learning and Security: Protecting Systems with Data and Algorithms, authors Clarence Chio and David Freeman have written a no-nonsense technical and practical guide showing how you can avoid that hype, and truly use machine learning to enhance information security.

After a brief introduction to what machine learning is, the authors candidly write of the limitations of machine learning in security. They note that the notion that machine learning methods will always give good results across different use cases is categorically false. In real-world scenarios there are usually factors to optimize for other than precision recall or accuracy.

For those that think that machine learning is the latest information security silver bullet, as good as this book is, it certainly won’t help them. But for those that know the limitations of machine learning, the authors suggest approaching it with equal parts enthusiasm and caution, remembering that not everything can instantly be made better with machine learning.

Machine learning works alongside areas such as pattern recognition and computational statistics, and as such, the book is made for those with a strong background in programming, math, and statistics. Most of the programming samples are in Python.

Current technologies like malware and virus classification, intrusion detection, malware classification, network protocol analysis and more are imperfect science. The promise of machine learning comes with many challenges. For those who are willing to invest in doing that, Machine Learning and Security is an indispensable reference.

This is a serious book for those serious about integrating machine learning into the overall information security framework. The reader is expected to know the underlying mathematics and statistics, Python and other languages, and more importantly – how to integrate these into their security architecture. Titles like Machine Learning For Dummies may provide a good introduction to the topic, but it’s books like this that will take you there.
Profile Image for Jari Pirhonen.
385 reviews9 followers
October 20, 2018
Machine learning are already used in security products and more opportunities lie ahead. Spam protection, malware detection and intrusion detection to mention a few. The book had lots of code examples and also descriptions of some methods to attack machine learning. This gave a good overview, but I have to admit I skipped the code examples.
Profile Image for AJ Sparks.
4 reviews
January 21, 2021
Very approachable and concise explanation of ML especially for someone with a security focused background. I got a lot out of this book! Some of the information feels a bit dated but still worth the read in my opinion.
Profile Image for Ethan J.
290 reviews11 followers
May 1, 2022
generally a quick glance - pretty general
Profile Image for Christine Lee.
21 reviews13 followers
January 9, 2021
Disclaimer: Only read the introduction and Android malware specific section for work purpose; skimmed through other sections.

Page 9 of this book has a "What is Machine Learning" section with the most concise and intuitive explanation of ML I have ever read. I would recommend this book not just to security specialists but for developers investigating into ML just for this clear picture of ML.

The book gives a good general outline and reference of tools for developing security applications using Machine Learning. For the Android malware section, I am currently using some of the tools mentioned in the book to build a mobile security product!

"What is Machine Learning" Excerpt:

Since the dawn of the technological age, researchers have dreamed of teaching computers to reason and make intelligent decisions in the way that humans do, by drawing generalizations and distilling concepts from complex information sets without explicit instructions.

Machine learning refers to one aspect of this goal- specifically, to algorithms and processes that learn in the sense of being able to generalize past data and experiences in order to predict future outcomes.

At the most general level, supervised machine learning methods adopt a Bayesian approach to knowledge discovery, using probabilities of previously observed events to infer the probabilities of new events. Unsupervised methods draw abstracts from unlabeled datasets and apply these to new data. Both families of methods can be applied to problems of classifications (assigning observations to categories) or regression (predicting numerical properties of an observation).
Displaying 1 - 6 of 6 reviews

Can't find what you're looking for?

Get help and learn more about the design.