AI and Emerging Topics in Cybersecurity

Key Details

Time commitment

• Total workload: 125 h
• Contact hours: 24 h
• Lecture: 12 h
• Hands-on/Tutorials: 6 h
• Seminar/discussion & guest-lecture: 2 h
• Flipped classroom: 4 h
• Group Project: 40
• Private study: 61 h

Assessment

• Mid-term assessment (proctored quiz) end of W5 (15%)
• Flipped classroom in W6 & W11 (10%)
• Group project from W6 to W12 (30%)
• Intermediate presentation (a pitch) in W8 (5%)
• Final presentation in W12 (12.5%)
• Technical report / scientific paper by W12 (12.5%)
• Final proctored exam (45%)

Register your interest

Subjects covered

Week 1: Security Operations & Cybersecurity Foundations

Summary:

Recap the essentials of cybersecurity, focusing on SOC operations and using the NIST Cybersecurity Framework as a reference. Bring students up to speed on fundamental concepts and ensure consistent prerequisite knowledge.

Lecture Content:

• NIST Cybersecurity Framework (Identify, Protect, Detect, Respond, Recover, Govern)
• Key SOC operations: vulnerability management, threat detection, incident response, red teaming, …
• SOC tools/technologies: SIEM, SOAR, IDS/IPS, EDR/NDR/XDR, TIP, …
• Standards and frameworks: NIST CSF, MITRE ATT&CK, CIS
• Data in SOC: Types, Values, and Significance
• Key SOC challenges: alert fatigue, evolving threats, APTs, …

Week 2: Data Science/Engineering Foundations

Summary:

Recap foundational concepts in data science and engineering with a focus on AI/ML.

Lecture Content:

• Data science/analytics concepts: statistical analysis. unsupervised and supervised ML, anomaly detection, neural networks, deep learning, reinforcement learning, CNN, RNNs, LSTM, …
• Data engineering concepts: data cleaning, normalization, enrichment, ETL, distributed data processing and big data architectures., …

Week 3: Rise of AI – Generative Models & LLMs

Summary:

Introduction to modern AI with a focus on generative models and LLMs. Bridge the gap between traditional data analytics and advanced AI concepts.

Lecture Content:

• Modern AI: Generative models and transformers.
• LLMs and their architecture.
• Applications of AI in Cybersecurity

Week 4: AI-powered Cyber Attack (Part 1)

Summary:

Explore how AI can be leveraged to automate and enhance cyber-attacks, guided by the MITRE ATT&CK framework.

Lecture Content:

• Introduction to cyber threat landscape: attackers TTPS
• AI-powered social engineering and phishing attacks (initial access).
• AI-generated malware (execution)

Week 5: AI-powered Cyber Defense (Part 1)

Summary:

Explore how AI strengthens cyber defense and improves SOC operations, guided by NIST Cybersecurity framework.

Lecture Content:

• AI for advanced threat detection and hunting.
• AI to enhance monitoring and reduce alert fatigue
• AI for automated incident response

Week 6: AI-powered Cyber Attack/Defense (Part 2) – Flipped Classroom

Summary:

A flipped classroom approach where students present on topics exploring AI applications in cyberattacks or defenses.

Lecture Content: (Potential Topics)

• AI-Driven Threat Intelligence
• AI for Secure Coding
• AI in Forensic Analysis and Incident Investigation
• AI for Adoptive Honeypots and Sandboxes
• AI-Powered Security Training and Awareness Programs
• AI for Penetration Testing and Red Team Operations
• AI for Vulnerability Management (Identification, Prioritization, and Patching)
• AI for Reporting and Summarization
• AI in Automated Reconnaissance
• AI for Automated Exploit Generation…

Week 7: AI-powered Cyber Attack/Defense (Part 3)

Summary:

Continuing the lecture series on AI for defensive and offensive security.

Lecture Content:

• The missing topics from week 6.
• Concerns & Considerations of AI in Cybersecurity

Week 8: Security Concerns in AI-driven Cybersecurity

Summary:

Addressing the security concerns and risks associated to AI systems and their usage in cybersecurity.

Lecture Content:

• AI-powered applications weaknesses & vulnerabilities.
• Adversarial Machine Learning (weaknesses & vulnerabilities of AI models).
• Related Frameworks: OWASP Machine Learning Security Top Ten, OWASP Top 10 for LLM Applications MITRE ATLAS, AIID, ADML.

Week 9: Reliability in AI-driven Cybersecurity

Summary:

Focusing on key considerations when applying AI systems in cybersecurity.

Lecture Content:

• Importance of explainability and interpretability in AI (Explainable AI – XAI).
• Building trust and ensuring accountability in AI-driven systems.
• Domain-specific AI models (RAG systems) and the importance of fine-tuning.
• Metrics and KPIs for benchmarking AI systems in cybersecurity (robustness, accuracy, security, etc.).

Week 10: Responsible AI-driven Cybersecurity

Summary:

Examine the ethical, legal, and regulatory concerns associated with AI, particularly in cybersecurity.

Lecture Content:

• Ethical considerations of AI systems: fairness, bias, and transparency.
• Privacy concerns with AI systems
• Legal and regulatory requirements for AI systems, e.g., GDPR, AI Act, etc.

–Emerging Cross-cutting Topics—

Week 11: Future Trends in AI & Cybersecurity

Flipped classroom + (optional) guest lecture

Summary:

Engage students (in form of flipped classroom) in exploring cutting-edge trends and controversial topics in AI and cybersecurity.

Guest lecture (if available) to provide industry insight.

Lecture Content: (potential topics)

• Post-quantum cryptography and AI’s role in post-quantum security
• AI in zero trust architecture
• Privacy-preserving AI & federated learning
• AI and its impact on cyber warfare
• AI in zero-day exploit discovery
• AI at the edge (from cloud computing to edge computing)
• Trust in the era of AI generated data
• Human-AI Collaboration
• AI-generated vulnerable codes

Week 12: Wrap-up

• Overview of the course.
• Final project presentations by students.
• Discussions.
• Guest lecture (from industry).

Register your interest

Learning objectives

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

LO1: Demonstrate well-developed knowledge of core AI concepts, including generative AI and large language models, and explain their relevance to cybersecurity operations.

LO2: Critically analyse the opportunities and limitations of AI in offensive and defensive cybersecurity applications, including within Security Operations Centers (SOCs).

LO3: Identify and assess vulnerabilities, adversarial threats, and ethical risks associated with the use of AI in cybersecurity.

LO4: Apply AI methods and tools to design and prototype solutions addressing real-world cybersecurity challenges in both defensive and offensive contexts.

LO5: Collaborate effectively in teams to develop and present AI-driven scenarios, integrating technical, organisational, and regulatory considerations.

LO6: Evaluate emerging trends and regulatory developments in AI for cybersecurity, anticipating their impact on professional practice and policy.

Register your interest