Schedule
Week-by-week topics, readings, and assignment deadlines, grouped by the course’s three
pillars. This table mirrors course-meta.json as the single source of truth. No required
textbook — readings (papers, tool docs, tutorials) are posted on Canvas per unit.
Overview
| Week | Dates | Pillar | Topic | Reading | Due | Lecture |
|---|---|---|---|---|---|---|
| 1 | Week 1 | Overview | Introduction and the Three Pillars of AI and Security | — | HW1 out (Wed) | lectures/wk01/ |
| 2 | Week 2 | AI for Security | Foundations of Machine Learning for Cybersecurity | — | HW1 due (Wed); HW2 out | lectures/wk02/ |
| 3 | Week 3 | AI for Security | Network Intrusion and Anomaly Detection | — | HW2 due (Wed); HW3 out | lectures/wk03/ |
| 4 | Week 4 | AI for Security | Malware Detection and Classification | — | HW3 due (Wed); HW4 out | lectures/wk04/ |
| 5 | Week 5 | AI for Security | Phishing/Fraud Detection and AI for Security Operations | — | HW4 due (Wed); HW5 out | lectures/wk05/ |
| 6 | Week 6 | Security of AI | Threat Modeling for ML Systems and Adversarial Examples | — | HW5 due (Wed); HW6 out; Midterm Project Proposal out | lectures/wk06/ |
| 7 | Week 7 | Security of AI | Advanced Evasion, Transferability, and Data Poisoning/Backdoors | — | HW6 due (Wed); Midterm Project work session | lectures/wk07/ |
| 8 | Week 8 | Security of AI | Midterm Project Work Session and Presentations | — | Midterm Project Report & Presentation due (Wed) | lectures/wk08/ |
| 9 | Week 9 | Security of AI | Model Extraction, Inversion, Membership Inference, and LLM Security | — | HW7 out (Mon) | lectures/wk09/ |
| 10 | Week 10 | Security of AI | Adversarial Defenses and Robustness | — | HW7 due (Wed); HW8 out | lectures/wk10/ |
| 11 | Week 11 | Trustworthy AI | Interpretability and Explainability | — | HW8 due (Wed); Capstone Project Proposal out | lectures/wk11/ |
| 12 | Week 12 | Trustworthy AI | Fairness: Definitions, Metrics, and Detection | — | Capstone Project Proposal due (Wed); Capstone Work Begins | lectures/wk12/ |
| 13 | Week 13 | Trustworthy AI | Fairness: Mitigation and Bias Correction | — | — | lectures/wk13/ |
| 14 | Week 14 | Trustworthy AI | Privacy-Preserving Machine Learning (Differential Privacy, Federated Learning) | — | HW9 out (Mon); Capstone Progress Report due (Wed) | lectures/wk14/ |
| 15 | Week 15 | Trustworthy AI | Robustness Certification, Formal Verification, and Safety | — | HW9 due (Wed) | lectures/wk15/ |
| 16 | Week 16 | Trustworthy AI | Transparency, Accountability, and AI Governance; Three-Pillar Synthesis | — | — | lectures/wk16/ |
| 17 | Week 17 | Synthesis | Capstone Presentations and Closing | — | Capstone Report due (Mon); Capstone Presentations (Mon–Wed) | lectures/wk17/ |
Pillar 1 — AI for Security (Weeks 2–5)
Using AI/ML to defend systems. Foundations of ML for cybersecurity, network intrusion and anomaly detection, malware detection and classification, and phishing/fraud detection plus AI-assisted security operations. Homework HW1–HW4 build the detectors students reuse later.
Pillar 2 — Security of AI (Weeks 6–10)
Protecting ML models from attack. Threat modeling and adversarial examples (FGSM/PGD), advanced evasion and transferability, data poisoning and backdoors, model extraction/inversion and membership inference, LLM security, and adversarial defenses and robustness. The Midterm Project (Weeks 6–8) and HW5–HW8 live here.
Pillar 3 — Trustworthy AI (Weeks 11–16)
Making AI safe, fair, robust, transparent, and accountable. Interpretability and explainability, fairness definitions/metrics and mitigation, privacy-preserving ML, robustness certification and formal verification, and transparency/accountability/governance, closing with a three-pillar synthesis. HW9 and the Capstone Project span this stretch.
Synthesis (Week 17): Capstone presentations integrate all three pillars.
Lecture materials are organized under lectures/wkNN/ in the course repository.
Related pages: Homework & Labs · Projects · Syllabus