Designing a Machine Learning Intrusion Detection System Defend Your Network from Cybersecurity Threats

  • Emmanuel Tsukerman

Your browser needs to be JavaScript capable to view this video

Try reloading this page, or reviewing your browser settings

You're watching a preview of subscription content. Log in to check access

This video will guide you on the principles and practice of designing a smart, AI-based intrusion detection system (IDS) to defend a network from cybersecurity threats.

The course begins by explaining the theory and state of the art of the field, and then proceeds to guide you on the step-by-step implementation of an ML-based IDS. The first part of the course will explain how an intrusion detection system is used to stop cybersecurity threats such as hackers from infiltrating your network. Next, it will explain why traditional intrusion detection systems are not able to keep up with the rapid evolution of black hat adversaries, and how machine learning offers a self-learning solution that is able to keep up with, and even outsmart them. Further, you will learn the high-level architecture of an ML-based IDS; how to carry out data collection, model selection, and objective selection (such as accuracy or false positive rate); and how all these come together to form a next-generation IDS. Moving forward, you’ll see how to implement the ML-based IDS.

What You Will Learn

  • Discover how an IDS works

  • See how machine learning-based IDSs are able to solve the problems that traditional IDSs have faced

  • Architect a machine learning-based IDS

  • Train the ML components of a next-generation IDS

  • Choose the correct metric function for your next-generation IDS in order to satisfy the most commonly encountered business objectives

Who This Video Is For

Cybersecurity professionals, data scientists, and students of these disciplines.

This video will guide you on the principles and practice of designing a smart, AI-based intrusion detection system (IDS) to defend a network from cybersecurity threats. The course begins by explaining the theory and then proceeds to guide you on the step-by-step implementation of an ML-based IDS.

About The Author

Emmanuel Tsukerman

Dr. Emmanuel Tsukerman graduated from Stanford University and UC Berkeley. He began his cybersecurity career in a small startup as a cybersecurity data scientist, where he developed a machine learning-based anti-ransomware solution that won the Top 10 Ransomware Products award by PC Magazine. In addition, Dr. Tsukerman designed a machine-learning malware detection system for Palo Alto Network’s firewall service, securing over 30,000 enterprise customers in real time. He is the author of the Machine Learning for Cybersecurity Cookbook and the popular courses “Cybersecurity Data Science” and “Machine Learning for Red Team Hackers”.

 

Supporting material

View source code at GitHub.

About this video

Author(s)
Emmanuel Tsukerman
DOI
https://doi.org/10.1007/978-1-4842-6591-8
Online ISBN
978-1-4842-6591-8
Total duration
52 min
Publisher
Apress
Copyright information
© Emmanuel Tsukerman 2020

Related content

Video Transcript

[MUSIC PLAYING]

Welcome to the course on designing a machine learning based intrusion detection system. I’m Dr. Tsukerman, an award winning cybersecurity data scientist, and I’ll be leading you through this course. In this course, you’re going to be learning how intrusion detection has never been as important as it is today. You’re going to be learning how machine learning is revolutionizing intrusion detection. What thinking goes into architecting? A next generation that is a machine learning based intrusion detection system. How to obtain collect and analyze intrusion detection data, use it for training, and how to select the best objective for your next generation intrusion detection system. Finally, I will conclude by covering the state of the art, so that you know what steps to take to go deeper into the field. Without further ado, let’s get started.