SIT719 - Security and Privacy Issues in Analytics

Year:

2020 unit information

Enrolment modes: Trimester 1: Burwood (Melbourne), Waurn Ponds (Geelong), Cloud (online)
Trimester 2: Burwood (Melbourne), Waurn Ponds (Geelong), Cloud (online)
Credit point(s): 1
EFTSL value: 0.125
Prerequisite:

Nil

Corequisite:

Nil

Incompatible with:

Nil

Study commitment

Students will on average spend 150 hours over the teaching period undertaking the teaching, learning and assessment activities for this unit.

Scheduled learning activities - campus

2 x 1 hour class per week, 1 x 1-hour workshop each week

 

Scheduled learning activities - cloud (online)

1 x 1 hour online seminar per fortnight.

Note:

The Cloud Campus offering of this unit uses the FutureLearn online learning platform. Learn more about studying through FutureLearn.

Content

As the size of computer networks has expanded the amount of data collected for network defence has greatly increased. A need has arisen for security experts that understand how to build analytics that make use of this data in order to detect or prevent attacks. This units will provide students with the fundamental tools to understand this area of cyber security. Students will examine this challenge from multiple perspectives. The unit starts from the basics of building scripts to answer questions of large packet captures as a foundational skillset. Once students are comfortable working with large data sets, they will use this new skill to study several supervised machine learning approaches and apply them to real world network datasets to build analytics that have been shown to be able to detect various malicious attacks. After becoming comfortable with supervised approaches, students will pivot to examining unsupervised methods for network defence, an important topic, since frequently there are insufficient available examples of malicious behaviour to train good models.

Finally students study the ethical implications of dealing with large datasets that arise in these contexts by examining privacy attacks that have been developed against large datasets and their associated analytics. All these topics will be explored through scaffolded programming assignments designed to be challenging for a student of any level of programming or mathematical experience. At the end of the unit students will have a solid grounding in how modern analytics work and how they can be applied to network defence.

Hurdle requirement

To be eligible to obtain a pass in this unit, students must meet certain milestones as part of the portfolio, and must achieve a passing grade in the examination.

Unit Fee Information

Click on the fee link below which describes you:

Talk to a Deakin adviser about studying at Deakin today

Call 1800 693 888Monday to Friday: 9am to 5pm AEDT
Chat live nowMonday to Friday: 8am to 7pm AEDT