Explore UCD

UCD Home >

COMP41870

Academic Year 2025/2026

AI Security: Offensive, Defensive, and Operational Best Practices (COMP41870)

Subject:
Computer Science
College:
Science
School:
Computer Science
Level:
4 (Masters)
Credits:
10
Module Coordinator:
Assoc Professor Nhien An Le Khac
Trimester:
Spring
Mode of Delivery:
Online
Internship Module:
No
How will I be graded?
Letter grades

Curricular information is subject to change.

This 'AI Security' module equips students with offensive and defensive techniques to secure AI Architectures, generative models, and AI-driven applications. Spanning background fundamentals, practical labs and policy frameworks the course ensures graduate can identify and mitigate security flaws while complying with emerging regulations and operating AI systems securely at scale.

About this Module

Learning Outcomes:

On Successful completion of this module the learner will be able to:

1. Explain foundational AI and cybersecurity concepts relevant to AI pipelines.
2. Identify and exploit vulnerabilities in AI models using recognised adversarial attack methods.
3. Devise and implement robust defenses (secure training, monitoring, adversarial mitigation) within modern practices.
4. Integrate governance, ethics, and compliance considerations (e.g., EU AI Act, bias) into AI security strategies.
5. Evaluate new threats and propose forward-looking solutions to secure AI systems against future attack trends.

Indicative Module Content:

1. AI Security Landscape
- AI Foundations - Architectures, Pipelines, and Machine Learning Frameworks
- Cybersecurity Essentials for AI - Attack Surfaces & Defensive Principles

2. Offensive Security
- Threat Modelling & Risk Assessment for AI
- Adversarial Attacks (CV & NLP)
- Generative AI Exploits & Prompt Injection
- Generative Agent Security Fundamentals
- Data Poisoning & Model Backdoors
- Privacy Attacks & Inference Risks

3. Defense
- Robust Training & Adversarial Defenses
- AI Security Policy Design & Implementation
- Monitoring, Logging, & Anomaly Detection
- Governance, Compliance & Ethical AI

4. Operational Best Practices & Emerging Topics
- Incident Response & AI Forensics
- Case Studies & Industry Insights
- Future Trends

Student Effort Hours:
Student Effort Type Hours
Lectures

20

Small Group

8

Autonomous Student Learning

172

Total

200


Approaches to Teaching and Learning:
active/task-based learning; lectures; critical writing; reflective learning; lab work; problem-based learning; case-based learning;

Requirements, Exclusions and Recommendations

Not applicable to this module.


Module Requisites and Incompatibles
Not applicable to this module.
 

Assessment Strategy
Description Timing Component Scale Must Pass Component % of Final Grade In Module Component Repeat Offered
Assignment(Including Essay): Assignment 1 Week 4 Alternative linear conversion grade scale 40% No
15
No
Assignment(Including Essay): Assignment 2 Week 8 Alternative linear conversion grade scale 40% No
15
No
Exam (In-person): Final exam End of trimester
Duration:
2 hr(s)
Alternative linear conversion grade scale 40% No
70
No

Carry forward of passed components
No
 

Resit In Terminal Exam
Summer Yes - 2 Hour
Please see Student Jargon Buster for more information about remediation types and timing. 

Feedback Strategy/Strategies

• Feedback individually to students, post-assessment

How will my Feedback be Delivered?

Not yet recorded.