Hands-On Machine Learning for Cybersecurity

Safeguard your system by making your machines intelligent using the Python ecosystem

Soma Halder , Sinan Ozdemir 지음

Packt(GCO Science) 2018년 12월 31일 출간

작품소개

책소개

▶Book Description
Cyber threats today are one of the costliest losses that an organization can face. In this book, we use the most efficient tool to solve the big problems that exist in the cybersecurity domain.

The book begins by giving you the basics of ML in cybersecurity using Python and its libraries. You will explore various ML domains (such as time series analysis and ensemble modeling) to get your foundations right. You will implement various examples such as building system to identify malicious URLs, and building a program to detect fraudulent emails and spam. Later, you will learn how to make effective use of K-means algorithm to develop a solution to detect and alert you to any malicious activity in the network. Also learn how to implement biometrics and fingerprint to validate whether the user is a legitimate user or not.

Finally, you will see how we change the game with TensorFlow and learn how deep learning is effective for creating models and training systems

▶What You Will Learn
？ Use machine learning algorithms with complex datasets to implement cybersecurity concepts
？ Implement machine learning algorithms such as clustering, k-means, and Naive Bayes to solve real-world problems
？ Learn to speed up a system using Python libraries with NumPy, Scikit-learn, and CUDA
？ Understand how to combat malware, detect spam, and fight financial fraud to mitigate cyber crimes
？ Use TensorFlow in the cybersecurity domain and implement real-world examples
？ Learn how machine learning and Python can be used in complex cyber issues

▶Key Features
？ Learn machine learning algorithms and cybersecurity fundamentals
？ Automate your daily workflow by applying use cases to many facets of security
？ Implement smart machine learning solutions to detect various cybersecurity problems

▶Who This Book Is For
This book is for the data scientists, machine learning developers, security researchers, and anyone keen to apply machine learning to up-skill computer security. Having some working knowledge of Python and being familiar with the basics of machine learning and cybersecurity fundamentals will help to get the most out of the book

목차

▶TABLE of CONTENTS
1: BASICS OF MACHINE LEARNING IN CYBERSECURITY
2: TIME SERIES ANALYSIS AND ENSEMBLE MODELING
3: SEGREGATING LEGITIMATE AND LOUSY URLS
4: KNOCKING DOWN CAPTCHAS
5: USING DATA SCIENCE TO CATCH EMAIL FRAUD AND SPAM
6: EFFICIENT NETWORK ANOMALY DETECTION USING K-MEANS
7: DECISION TREE AND CONTEXT-BASED MALICIOUS EVENT DETECTION
8: CATCHING IMPERSONATORS AND HACKERS RED HANDED
9: CHANGING THE GAME WITH TENSORFLOW
10: FINANCIAL FRAUD AND HOW DEEP LEARNING CAN MITIGATE IT
11: CASE STUDIES

책 속으로

▶What this book covers
？ Chapter 1, Basics of Machine Learning in Cybersecurity, introduces machine learning and its use cases in the cybersecurity domain. We introduce you to the overall architecture for running machine learning modules and go, in great detail, through the different subtopics in the machine learning landscape.

？ Chapter 2, Time Series Analysis and Ensemble Modeling, covers two important concepts of machine learning: time series analysis and ensemble learning. We will also analyze historic data and compare it with current data to detect deviations from normal activity.

？ Chapter 3, Segregating Legitimate and Lousy URLs, examines how URLs are used. We will also study malicious URLs and how to detect them, both manually and using machine learning.

？ Chapter 4, Knocking Down CAPTCHAs, teaches you about the different types of CAPTCHA and their characteristics. We will also see how we can solve CAPTCHAs using artificial intelligence and neural networks.

？ Chapter 5, Using Data Science to Catch Email Fraud and Spam, familiarizes you with the different types of spam email and how they work. We will also look at a few machine learning algorithms for detecting spam and learn about the different types of fraudulent email.

？ Chapter 6, Efficient Network Anomaly Detection Using k-means, gets into the various stages of network attacks and how to deal with them. We will also write a simple model that will detect anomalies in the Windows and activity logs.

？ Chapter 7, Decision Tree- and Context-Based Malicious Event Detection, discusses malware in detail and looks at how malicious data is injected in databases and wireless networks. We will use decision trees for intrusion and malicious URL detection.

？ Chapter 8, Catching Impersonators and Hackers Red Handed, delves into impersonation and its different types, and also teaches you about Levenshtein distance. We will also learn how to find malicious domain similarity and authorship attribution.

？ Chapter 9, Changing the Game with TensorFlow, covers all things TensorFlow, from installation and the basics to using it to create a model for intrusion detection.

？ Chapter 10, Financial Fraud and How Deep Learning Can Mitigate It, explains how we can use machine learning to mitigate fraudulent transactions. We will also see how to handle data imbalance and detect credit card fraud using logistic regression.

？ Chapter 11, Case Studies, explores using SplashData to perform password analysis on over one million passwords. We will create a model to extract passwords using scikit-learn and machine learning.

출판사 서평

▶ Preface
The damage that cyber threats can wreak upon an organization can be incredibly costly. In this book, we use the most efficient and effective tools to solve the big problems that exist in the cybersecurity domain and provide cybersecurity professionals with the knowledge they need to use machine learning algorithms. This book aims to bridge the gap between cybersecurity and machine learning, focusing on building new and more effective solutions to replace traditional cybersecurity mechanisms and provide a collection of algorithms that empower systems with automation capabilities.

This book walks you through the major phases of the threat life cycle, detailing how you can implement smart solutions for your existing cybersecurity products and effectively build intelligent and future-proof solutions. We'll look at the theory in depth, but we'll also study practical applications of that theory, framed in the contexts of real-world security scenarios. Each chapter is focused on self-contained examples for solving realworld concerns using machine learning algorithms such as clustering, k-means, linear regression, and Naive Bayes.

We begin by looking at the basics of machine learning in cybersecurity using Python and its extensive library support. You will explore various machine learning domains, including time series analysis and ensemble modeling, to get your foundations right. You will build a system to identify malicious URLs, and build a program for detecting fraudulent emails and spam. After that, you will learn how to make effective use of the k-means algorithm to develop a solution to detect and alert you about any malicious activity in the network. Also, you'll learn how to implement digital biometrics and fingerprint authentication to validate whether the user is a legitimate user or not.

This book takes a solution-oriented approach to helping you solve existing cybersecurity issues.

작가정보

저자(글) Soma Halder

Soma Halder is the data science lead of the big data analytics group at Reliance Jio Infocomm Ltd, one of India's largest telecom companies. She specializes in analytics, big data, cybersecurity, and machine learning. She has approximately 10 years of machine learning experience, especially in the field of cybersecurity. She studied at the University of Alabama, Birmingham where she did her master's with an emphasis on Knowledge discovery and Data Mining and computer forensics. She has worked for Visa, Salesforce, and AT&T. She has also worked for start-ups, both in India and the US (E8 Security, Headway ai, and Norah ai). She has several conference publications to her name in the field of cybersecurity, machine learning, and deep learning.

저자(글) Sinan Ozdemir

Sinan Ozdemir is a data scientist, start-up founder, and educator living in the San Francisco Bay Area. He studied pure mathematics at the Johns Hopkins University. He then spent several years conducting lectures on data science there, before founding his own start-up, Kylie ai, which uses artificial intelligence to clone brand personalities and automate customer service communications. He is also the author of Principles of Data Science, available through Packt.