Data Analytics for Cyber Security

CT115-3-M (Version E)

Introduction and Module Overview

 Lecturer Information

• Lecturer Name: Assoc. Prof. Dr. Thang Ka Fei

• Email: [Link]@[Link]
• Consultation Hours: Book via MS Teams messaging.

Module Code & Module Title Slide Title SLIDE 2

 Pre-Requisites For This Module

• Nil.

Module Code & Module Title Slide Title SLIDE 3

 Outcomes Based Education

• OBE is education based on producing particular educational outcomes that:

Ø Focus on what students can actually do after they are taught.
Ø Expect all learners / students to successfully achieve particular (sometimes minimum) level of
knowledge and abilities.

• It’s NOT what We want to teach.

• It’s WHAT You should learn.

Module Code & Module Title Slide Title SLIDE 4

 Aims of this Module

1. This module will familiarise students with models and algorithms for machine
learning, reinforcing the thesis of injecting data analytics into security operations
to efficiently uncover patterns and identify indicators of compromise.

2. The theory and principles will be presented with a focus on practical experience
with using industry standard frameworks for implementation and using data
visualization techniques and strategies to communicate information.

3. This will prepare them to critically assess and evaluate business problems using
pattern discovery and predictive modelling in research or industry applications.

Module Code & Module Title Slide Title SLIDE 5

 Module Learning Outcomes

CLO Learning Outcomes Assessment

1 Explain the procedures of data analysis with appropriate Class Test

machine learning technique based on the scenario of a cyber
attack (C5,PLO2)
2 Appraise the most suitable technique or method to uncover Assignment 1 (Individual)
patterns and extract valuable insights of a possible cyber
attack (C4, PLO7)
3 Perform data analysis using suitable machine learning Assignment 2 (Group)
techniques to detect attack signatures and identify relevant
evidence (A5, PLO6)

Module Code & Module Title Slide Title SLIDE 6

 Mapping of CLO with PLO

PLO 1 PLO 2 PLO 3 PLO 4 PLO 5 PLO 6 PLO 7 PLO 8 PLO 9 PLO 10 PLO 11 PLO12

CLO1 ü

CLO2 ü

CLO3 ü

The learning domains are:

PLO2: Cognitive Skills
PLO6: Digital Skills
PLO7: Numeracy Skills

Module Code & Module Title Slide Title SLIDE 7

 Student Learning Time

• Module Credit Value: 3

• Total Learning Hours: 120 per semester

Lecture 18 hours

Tutorial 0 hours

Practical 24 hours

Others 0 hours

Independent Learning Time 76 hours

Assessment 2 hours

Total Learning Hours 120 hours per semester

Module Code & Module Title Slide Title SLIDE 8

 Module Content Outline
Week Topic
1 Machine Learning Methods
2 Machine Learning Model Logic
3 Machine Learning Pipeline
4 Data Preprocessing for Machine Learning
5 Machine Learning Performance Evaluation
6 Machine Learning: Algorithms in Practice
7 Model Optimisation Strategies
8 Assignment Briefing
9 Model Selection
10 Machine Learning: Review & Revision
11 Deep Learning
12 Natural Language Processing

Module Code & Module Title Slide Title SLIDE 9

 Assessment Summary (refer to module handbook and module descriptor)

Form of Assessment Methods Hand Out Date Hand In Date %

Assessment
Continuous Assignment: 8th Week 12th Week 70%
Assessment Individual – 50%
Group – 20%
Final Class Test 11th week 11th week 30%
Assessment

Assessment requirement:
To pass the module, you must attempt every element of assessment and achieve at least 50% in the module overall.

Module Code & Module Title Slide Title SLIDE 10

 Expectations

1. Abide by ALL rules and regulations of APU.

2. Proper attire.
3. No speaking of dialects during class.
4. Attendance is compulsory. Valid Medical Certs must be supported in any absence from class.
5. Three cases of Late will be equal to 1 absence.
6. Use proper academic references – APA Referencing only.
7. Academic Dishonesty / Plagiarism is a serious offence. Any suspicions will be referred to the
University’s Academic Dishonesty Board.
8. Formal assessments must be submitted on time in the specified format given. Failure to meet
deadlines will be treated as non-submission and no marks will be awarded. Incomplete submissions
will be subjected to penalty of mark deductions or forfeit.

Module Code & Module Title Slide Title SLIDE 11

 Achievement Requirements:
Postgraduate Programmes

Marks Alphabetical Grade Grading Point Classification

80-100 A+ 4.0
Distinction
75-79 A 3.8
70-74 B+ 3.6
Merit
65-69 B 3.5
60-64 C+ 3.3
55-59 C 3.2 Pass
50-54 C- 3.0
40-49 D 2.5 Fail (marginal)
30-39 F+ 2.0 Fail
20-29 F 1.5 Fail
10-19 F- 1.0 Fail
0-9 U 0 Unclassified

Module Code & Module Title Slide Title SLIDE 12

 Reference Materials

Course Materials available in Moodle Essential and Further Readings

• Module handbook • Aurélien Géron (2022). Hands-On Machine Learning
with Scikit-Learn, Keras, and TensorFlow: Concepts,
• Module descriptor Tools, and Techniques to Build Intelligent Systems (3rd
Edition). O'Reilly Media; ISBN: 978-1098125974
• Lecture slides • Jason Brownlee (2021). Machine Learning Mastery
With Python: Understand Your Data, Create Accurate
• Tutorial/Lab materials Models and Work Projects End-To-End. Independently
• Sample incourse questions & answers published; ISBN: 979-8540446273

• Sample exam questions & answers *Further readings will be assigned from time to time.

Module Code & Module Title Slide Title SLIDE 13

 Your Valuable Feedback
• You are welcome to discuss your views on this module at any point of time.
• Do fill in anonymous evaluation questionnaires in the student feedback form.
There are two points - mid and end of the teaching semester.
• The feedbacks you provide will be constructive for improvement of teaching and
module content development.

Module Code & Module Title Slide Title SLIDE 14