Machine Learning for Network Security

Introduction:

With advancement in technology, organizations are now able to collect a large amount of data that are being generated and transferred over the network. Cybersecurity experts may have a hard time monitoring and analysing this data due to the sheer volume which is beyond their capacity to manage. One possible solution that is being widely explored is to use Machine Learning and Data Mining methods for cybersecurity related problems.

Methods of machine learning and data mining can help to build better detectors from massive amounts of complex data that is generated over the Internet. Such methods can also help discover the information required to build more secure systems.

Data can be gathered from a combination of software installed on customer workstations and sensors placed in network segments. This data can be fed to systems that use machine learning which can classify the incoming samples and can distinguish between normal behavior and any anomalies. Historical data and patterns can be used to compare samples and identify evolving threats.

This course will give you a broad introduction to network security and related cybersecurity problems. It will also explore various machine learning and data mining solutions to cybersecurity problems.

Course Objectives:

  • Introduction to Network Security concepts
  • Basic Functions of Firewalls
  • Intrusion Detection and Prevention Systems
  • Collections of application and network data
  • Apply machine learning solutions to cybersecurity problems

Duration

7 hours, 1 Day Course

Mode of Delivery

Classroom-based, Instructor-led Training

Course Outlines

  1. Introduction to Network Security Concepts
    1. Challenges to Securing Information
    2. Core principles of Information Security
    3. Types of Network Attacks
    4. Malware
  2. Introduction to Firewalls
    1. Types of Firewalls
    2. Firewall Design and Architecture
    3. Configuring Firewalls
  3. Intrusion Detection and Prevention Systems
    1. Types of IDS
    2. Host and Network based IDS
    3. IPS
    4. Honeypots
    5. Introduction to Snort
  4. Introduction to Data Mining and Machine Learning Concepts
    1. Supervised /Unsupervised Machine Learning Methods
    2. Challenges in Data Mining and Machine Learning
  5. Data Collection and Analysis
    1. Machine Learning for Anomaly Detection
    2. Machine Learning in Intrusion Detection
    3. Machine Learning and Network Traffic
    4. Emerging Challenges in Cybersecurity
  6. Network Forensics
    1. Forensic Principles
    2. Capturing Network Traffic
    3. Use of Cyber Forensic Tools
    4. Legal issues