Mastering Machine Learning for Penetration Testing电子书

Title Page

Copyright and Credits

Mastering Machine Learning for Penetration Testing

Dedication

Packt Upsell

Why subscribe?

PacktPub.com

Contributors

About the author

About the reviewer

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Introduction to Machine Learning in Pentesting

Technical requirements

Artificial intelligence and machine learning

Machine learning models and algorithms

Supervised

Bayesian classifiers

Support vector machines

Decision trees

Semi-supervised

Unsupervised

Artificial neural networks

Linear regression

Logistic regression

Clustering with k-means

Reinforcement

Performance evaluation

Dimensionality reduction

Improving classification with ensemble learning

Machine learning development environments and Python libraries

NumPy

SciPy

TensorFlow

Keras

pandas

Matplotlib

scikit-learn

NLTK

Theano

Machine learning in penetration testing - promises and challenges

Deep Exploit

Summary

Questions

Further reading

Phishing Domain Detection

Technical requirements

Social engineering overview

Social Engineering Engagement Framework

Steps of social engineering penetration testing

Building real-time phishing attack detectors using different machine learning models

Phishing detection with logistic regression

Phishing detection with decision trees

NLP in-depth overview

Open source NLP libraries

Spam detection with NLTK

Summary

Questions

Malware Detection with API Calls and PE Headers

Technical requirements

Malware overview

Malware analysis

Static malware analysis

Dynamic malware analysis

Memory malware analysis

Evasion techniques

Portable Executable format files

Machine learning malware detection using PE headers

Machine learning malware detection using API calls

Summary

Questions

Further reading

Malware Detection with Deep Learning

Technical requirements

Artificial neural network overview

Implementing neural networks in Python

Deep learning model using PE headers

Deep learning model with convolutional neural networks and malware visualization

Convolutional Neural Networks (CNNs)

Recurrent Neural Networks (RNNs)

Long Short Term Memory networks

Hopfield networks

Boltzmann machine networks

Malware detection with CNNs

Promises and challenges in applying deep learning to malware detection

Summary

Questions

Further reading

Botnet Detection with Machine Learning

Technical requirements

Botnet overview

Building a botnet detector model with multiple machine learning techniques

How to build a Twitter bot detector

Visualization with seaborn

Summary

Questions

Further reading

Machine Learning in Anomaly Detection Systems

Technical requirements

An overview of anomaly detection techniques

Static rules technique

Network attacks taxonomy

The detection of network anomalies

HIDS

NIDS

Anomaly-based IDS

Building your own IDS

The Kale stack

Summary

Questions

Further reading

Detecting Advanced Persistent Threats

Technical requirements

Threats and risk analysis

Threat-hunting methodology

The cyber kill chain

The diamond model of intrusion analysis

Threat hunting with the ELK Stack

Elasticsearch

Kibana

Logstash

Machine learning with the ELK Stack using the X-Pack plugin

Summary

Questions

Evading Intrusion Detection Systems

Technical requirements

Adversarial machine learning algorithms

Overfitting and underfitting

Overfitting and underfitting with Python

Detecting overfitting

Adversarial machine learning

Evasion attacks

Poisoning attacks

Adversarial clustering

Adversarial features

CleverHans

The AML library

EvadeML-Zoo

Evading intrusion detection systems with adversarial network systems

Summary

Questions

Further reading

Bypassing Machine Learning Malware Detectors

Technical requirements

Adversarial deep learning

Foolbox

Deep-pwning

EvadeML

Bypassing next generation malware detectors with generative adversarial networks

The generator

The discriminator

MalGAN

Bypassing machine learning with reinforcement learning

Reinforcement learning

Summary

Questions

Further reading

Best Practices for Machine Learning and Feature Engineering

Technical requirements

Feature engineering in machine learning

Feature selection algorithms

Filter methods

Pearson's correlation

Linear discriminant analysis

Analysis of variance

Chi-square

Wrapper methods

Forward selection

Backward elimination

Recursive feature elimination

Embedded methods

Lasso linear regression L1

Ridge regression L2

Tree-based feature selection

Best practices for machine learning

Information security datasets

Project Jupyter

Speed up training with GPUs

Selecting models and learning curves

Machine learning architecture

Coding

Data handling

Business contexts

Summary

Questions

Further reading

Assessments

Chapter 1 – Introduction to Machine Learning in Pentesting

Chapter 2 – Phishing Domain Detection

Chapter 3 – Malware Detection with API Calls and PE Headers

Chapter 4 – Malware Detection with Deep Learning

Chapter 5 – Botnet Detection with Machine Learning

Chapter 6 – Machine Learning in Anomaly Detection Systems

Chapter 7 – Detecting Advanced Persistent Threats

Chapter 8 – Evading Intrusion Detection Systems with Adversarial Machine Learning

Chapter 9 – Bypass Machine Learning Malware Detectors

Chapter 10 – Best Practices for Machine Learning and Feature Engineering

Other Books You May Enjoy

Leave a review - let other readers know what you think