Module COMP41870 – AI Security (from 2025/2026)
Module Lecturer: Dr. Aditya Kuppa
What Will I learn?
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 graduates can identify and mitigate security flaws while complying with emerging regulations and operating AI systems securely at scale.
Module Learning Outcomes:
On successful completion of this module the learner will be able to:
- Explain foundational AI and cybersecurity concepts relevant to AI pipelines.
- Identify and exploit vulnerabilities in AI models using recognized adversarial attack methods.
- Devise and implement robust defenses (secure training, monitoring, adversarial mitigation) within modern practices.
- Integrate governance, ethics, and compliance considerations (e.g., EU AI Act, bias) into AI security strategies.
- Evaluate new threats and propose forward-looking solutions to secure AI systems against future attack trends.
Module Dependencies/ Prerequisites:
The students are required to have the background of:
- Introductory Cybersecurity: Understanding of threat modeling, network security basics (required).
- Python programming: Proficiency in coding, debugging, and using Python-based (required).
How will I learn? Student Effort Hours: 200h (28h contact time, 172h autonomous learning)
How will I be assessed? Continuous Assessment: 30% – Two assignments; End of Semester Formal Examination: 70%
What happens if I fail? Resit, within 2 trimesters, Resit in summer.
—————————————————————————————————————-
Module COMP41880 – AI Investigations (from 2025/2026)
Module Coordinator & Lecturer: Assoc. Prof. Nhien-An Le-Khac
What Will I learn?
This module aims to train students in two critical areas:
- Using AI to Support Investigations
- Investigating AI/Generative AI Systems
This module integrates theoretical foundations (algorithms, interpretability methods, regulatory knowledge) with hands-on practice (labs, case studies, project work) to prepare students for next generation roles in law enforcement, digital forensics, compliance, and AI governance.
Module Learning Outcomes:
On successful completion of this module the learner will be able to:
- Understand foundation concepts of AI
- Apply AI methods to gather, analyze, and interpret digital evidence in investigative scenarios.
- Investigate AI systems (including Generative AI), identifying biases, verifying system integrity, and explaining decision processes using modern XAI (Explainable AI) techniques
- Evaluate legal, ethical, and regulatory requirements governing AI usage in investigations.
Module Dependencies/ Prerequisites:
- Fundamentals on Cybersecurity or Digital Forensics (Required):
- Background knowledge on Data Analysis or Machine Learning (Recommended)
- Programming Skills: Python for data manipulation and ML library usage (Recommended).
How will I learn? Student Effort Hours: 200h (28h contact time, 172h autonomous learning)
How will I be assessed? Continuous Assessment: 30% – Two assignments; End of Semester Formal Examination: 70%
What happens if I fail? Resit, within 2 trimesters, Resit in summer.