Courses Offered

COMP3523 Security and Privacy in Artificial Intelligence

2025-26

Instructor(s):

Chen Ho

(Class A)

No. of credit(s):

Recommended Learning Hours:

Lecture:	36.0
Tutorial:	3.0

Pre-requisite(s):

COMP3314

Co-requisite(s):

Mutually exclusive with:

Remarks:

Course Learning Outcomes

1.	[Foundation] Be able to understand the principles and objectives of the security and privacy of artificial intelligence.
2.	[Model] Be able to understand AI security models and to apply the model to achieve the security objectives.
3.	[Design] Be able to understand the basic principles of AI security design and to apply the principles.
4.	[Application] Be able to understand the security issues of practical AI systems.
5.	[Application development] Be able to implement practical AI systems in a secure manner.

Mapping from Course Learning Outcomes to Programme Learning Outcomes
	PLO a	PLO b	PLO c	PLO d	PLO e	PLO f	PLO g	PLO h	PLO i	PLO j
CLO 1			T,P			T,P		T,P
CLO 2		T,P	T,P							T,P
CLO 3	T,P			T,P					T,P	T,P
CLO 4				T,P		T,P		T,P		T,P
CLO 5			T,P	T,P	T,P		T,P

T - Teach, P - Practice
For BEng(CompSc) Programme Learning Outcomes, please refer to here.

Syllabus

Calendar Entry:
This course will equip students with the knowledge and hands-on experience to develop secure, privacy-preserving AI systems. As AI becomes increasingly integrated into our everyday lives, students will explore how seemingly powerful AI systems can be compromised through various attacks that manipulate decision-making processes and steal private information. Students will also learn about cutting-edge defenses designed to protect these systems. By the end of the course, students will be able to assess security and privacy risks when designing AI-driven solutions and implement effective countermeasures.

Detailed Description:

Introduction to security and privacy	Mapped to CLOs
Introduction to security and privacy	1, 2
Introduction to machine learning	Mapped to CLOs
Introduction to machine learning	2, 3
Security and privacy in CNN	Mapped to CLOs
Security and privacy in CNN	2, 3
Security and privacy in LLM	Mapped to CLOs
Security and privacy in LLM	4, 5
Security and privacy in AI agents	Mapped to CLOs
Security and privacy in AI agents	4, 5

Assessment:
Continuous Assessment: 50%
Written Examination: 50%

Teaching Plan

Please refer to the corresponding Moodle course.

Moodle Course(s)

Courses Offered

COMP3523 Security and Privacy in Artificial Intelligence

Sign in to your account

Sign in to your account