FIT5230 Malicious AI
Faculty of Information Technology
FIT5230 Malicious AI is a level 5, 6-credit-point, postgraduate unit from the Faculty of Information Technology. It isn't offered in 2023. It needs FIT9136.
- Credit points
- 6
- Offered in 2023
- Not offered
- Assessment
- Exam 50%
- and 4 other tasks
- Workload
- 144 hours
- per semester
This is the 2023 handbook entry. See the 2027 entry.
Reviews
No reviews yetNo reviews yet. Be the first to review FIT5230.
Requisites
Before FIT5230
Corequisites
Pass these before, or take them in the same semester.
Prerequisites
Pass these before you enrol.
After FIT5230
No unit lists FIT5230 as a prerequisite in the 2023 handbook.
Overview
In this unit you will learn first-hand the required skills to eventually become a Chief AI / Data Officer. You will be exposed to the latest technologies deployed by attackers against AI and security, and mechanisms to counter these malicious activities.
This unit will offer you the opportunity to be engaged in role-playing case studies wherein the coursework assessments will require you to be pitched against each other in a security warfare: security vs anti-security technologies, such as, deepfakes vs anti-deepfakes, adversarial machine learning vs counter adversarial machine learning.
Offerings in 2023
The 2023 handbook lists no offerings for FIT5230.
Assessment
- Assignment Milestone 1AssignmentThreshold hurdle2%
- Assignment Milestone 2AssignmentThreshold hurdle8%
- Assignment Milestone 3AssignmentThreshold hurdle25%
- Assignment Milestone 4AssignmentThreshold hurdle15%
- Scheduled final assessment (2 hours and 10 minutes)ExamThreshold hurdle50%
Learning outcomes
When you finish this unit, you should be able to:
- 1
identify and analyse malicious technologies deployed by attackers against AI and security such as adversarial machine learning, deepfakes, generative adversarial networks, anti-security;
- 2
devise counter-anti-AI security technologies to combat the anti-AI security techniques deployed by attackers;
- 3
design and formulate AI security or anti-AI security techniques in real-world situations;
- 4
critically assess the level of security offered by existing AI and security systems;
- 5
expose students to the ethical principles and consequences between the dark side and AI for social good.
Workload and teaching
- Workshops24 hours
- Laboratories24 hours
- Teaching approachPeer assisted learning
- Teaching approachActive learning
- Teaching approachRole play
Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities.
Contacts
- Chief Examiners
- Professor Raphael Phan
Common questions
What are the prerequisites for FIT5230?
You need FIT9136 before you enrol; and FIT5197 or FIT5047 before or alongside it.
When is FIT5230 offered?
FIT5230 has no offerings listed in the 2023 handbook.
How much work is FIT5230?
The handbook expects about 144 hours of study across the semester. No students have rated its difficulty yet.
Does FIT5230 have an exam?
Yes. The exam is worth 50% of the final mark, alongside 4 other tasks.