Weekly Materials

Readings, discussions, and activities for each week

Week 1

Course Overview: Rationale for Secure & Trustworthy AI

Section 1 - WHY

Topics

  • 1.1 Course introduction and objectives

Reading: Hendrycks Chapter 6

Due: Assignment 1 (Mon, Jan 26)

Presentation: Pres 1 — Course Overview

View Week 1 →
Week 2

Ethics, Values, and Human Impact of AI

Section 1 - WHY

Topics

  • 1.2 Societal stakes: the transformative promise and risk of AI systems
  • 1.3 Overview of prominent failures, scandals, and incidents
  • 1.4 Influence of AI on society, economy, and geopolitics
  • 2.1 Philosophical ethical frameworks applied to AI systems

Reading: Hendrycks Chapter 6

Due: Assignment 1 (Mon, Jan 26)

Given: Assignment 2 (Wed, Jan 28)

Presentations: Pres 2 — Ethics & Values · Pres 2.5 — Assignment 1 Insights

View Week 2 →
Week 3

AI Values, Human Rights, and Human-AI Collaboration

Section 1 - WHY

Topics

  • 2.2 Core AI values: fairness, transparency, accountability, privacy, autonomy, safety, and sustainability
  • 2.3 AI and human rights: cross-cultural, legal, and environmental perspectives
  • 2.4 Human-AI collaboration: designing systems that augment rather than replace human capabilities

Reading: Hendrycks Chapter 1

Due: Assignment 2 (Mon, Feb 2)

Given: Assignment 3 (Wed, Feb 4)

Presentations: Pres 3 — Core AI Values and Human Rights · Pres 4 — Human-AI Collaboration

View Week 3 →
Week 4

Potential Harms, Misuse, and the Alignment Problem

Section 1 - WHY

Topics

  • 3.1 Unintended harms: algorithmic bias and discrimination in criminal justice, hiring, lending, and healthcare
  • 3.2 Intentional misuse: deepfakes, coordinated misinformation, surveillance, autonomous cybercrime, and malicious applications
  • 3.3 The alignment problem, value learning, and catastrophic risks

Reading: Hendrycks Chapter 1

Due: Assignment 3 (Thu, Feb 12)

Given: Assignment 4 (Wed, Feb 11)

Presentations: Pres 5 — Unintended Harms: Bias and Discrimination · Pres 6 — Intentional Misuse and the Alignment Problem

View Week 4 →
Week 5

Regulatory and Legal Context for AI

Section 1 - WHY

Topics

  • 4.1 International AI governance: GDPR, EU AI Act, and emerging global frameworks
  • 4.2 U.S. AI regulation: CCPA, Executive Orders, and sectoral requirements
  • 4.3 Organizational frameworks: NIST AI RMF, ISO standards, and industry best practices
  • 4.4 Documentation and auditability: model cards, datasheets, and transparency reporting

Reading: Hendrycks Chapter 8

Due: Assignment 4 (Wed, Feb 18)

Presentations: Pres 7 — International and U.S. AI Governance · Pres 8 — Organizational Frameworks, Documentation & Auditability

View Week 5 →
Week 6

Biology, Neuroscience, and Psychology connections to AI/ML Systems, Lifecycles, and Security

Section 2 - WHAT

Topics

  • 5.1 Biology, Neuroscience, and Psychology connections to AI/ML
  • 5.2 Core architecture of modern AI/ML systems and how they differ from traditional software
  • 5.3 AI/ML system lifecycles: data collection, model training, deployment, and monitoring

Reading: Hendrycks Chapter 2

Given: Assignment 5 (Thu, Feb 26)

Presentation: Pres 9 — Biology, Neuroscience & Psychology of AI/ML

View Week 6 →
Week 7

AI/ML Lifecycle Vulnerabilities, LLM-Specific Vulnerabilities, and Threat Modeling Frameworks

Section 2 - WHAT

Topics

  • 6.1 AI/ML lifecycle vulnerabilities: data poisoning, backdoors, adversarial examples
  • 6.2 ML attack vectors across the 4-stage pipeline
  • 6.3 LLM-specific vulnerabilities: data-control path, hallucination, sycophancy, deception
  • 6.4 AI/ML threat modeling frameworks: OWASP, ATLAS, MAESTRO, AIUC-1

Reading: Hendrycks Chapter 2

Due: Assignment 5 (Thu, Mar 4)

Presentations: Pres 10 — Attacking the AI/ML Pipeline · Pres 11 — LLM Vulnerabilities & Threat Modeling

View Week 7 →
Week 8

Midterm Review

Section 2 - WHAT

Topics

  • 1.1-6.4 Comprehensive review of all topics covered in Units 1-6

Given: Assignment 6 (Wed, Mar 11)

Presentations: Pres 12 — Natural Learning, Reward Hacking & the University Education Model · Pres 13 — Midterm Review

View Week 8 →
Week 9

Midterm Exam and Midterm Project Assignment

Section 2 - WHAT

Topics

  • -- Midterm Exam (Mon, Mar 23)
  • -- Midterm Project assigned (Wed, Mar 25)

Midterm Exam: Monday, Mar 23

Due: Assignment 6 (Wed, Mar 25)

Given: Midterm Project (Wed, Mar 25)

Presentation: Pres 14 — LLM-Assisted Development & the Midterm Project

View Week 9 →
Week 10

Privacy, Bias, Transparency, and Explainability

Section 2 - WHAT

Topics

  • 7.1 Privacy risks in AI: membership inference, data leakage, surveillance, and predictive harm
  • 7.2 Bias in AI systems: types, sources, and fairness evaluation frameworks
  • 7.3 Algorithmic transparency and accountability in high-stakes decision-making
  • 7.4 Explainability and interpretability: concepts, techniques, and tools

Reading: Hendrycks Chapters 3-4

Due: Midterm Project (Wed, Apr 8)

Presentations: Pres 15 — Privacy Risks & Bias · Pres 16 — Transparency & Explainability

Interactive Demo: Bias, Transparency, Explainability, and Interpretability

View Week 10 →
Week 11

Privacy-Preserving ML and Secure Computation

Section 3 - HOW

Topics

  • 8.1 Differential privacy: concepts, mechanisms, and privacy-utility tradeoffs
  • 8.2 Federated learning: architecture, security considerations, and applications
  • 8.3 Homomorphic encryption: principles and use cases for computation on encrypted data
  • 8.4 Secure multi-party computation: collaborative learning without exposing private data

Presentation: Pres 17 — Differential Privacy & Federated Learning

Interactive Demo: Differential Privacy & Federated Learning

View Week 11 →
Week 12

Testing & Evaluation for AI/ML Systems

Section 3 - HOW

Topics

  • 9.1 Security testing methodologies and vulnerability assessment for AI/ML systems
  • 9.2 Evaluation: benchmarks, metrics, datasets, and tools

Presentation: Pres 18 — Testing, Evaluation & the Road to Red-Teaming

View Week 12 →
Week 13

Red-Teaming & Operationalizing Secure AI

Section 3 - HOW

Topics

  • 9.3 Red-teaming: adversarial approaches, attack simulation, and penetration testing
  • 10.3–10.5 Context management, security controls & guardrails, operational practices

Presentations:

Pres 19 — Red-Teaming AI Systems

Pres 20 — Building & Operationalizing Secure AI

View Week 13 →
Week 14

Risk, Audit, Industry Landscape & Career Pathways

Section 3 - HOW + Section 4 - SYNTHESIS

Topics

  • 11 Risk management and crisis response: NIST AI RMF, governance, incident response
  • 12 Independent auditing, documentation, and disclosure: model cards, third-party evaluation
  • 13 Industry applications and emerging challenges: sector-specific, policy debates, current landscape, emerging tech
  • 14 Professionalism, pathways, and future directions: career pathways, certifications, final-project workshop

Presentations: Pres 21 — Units 11, 12, 13 + Weekend Briefing · Pres 22 — Unit 14: Career Pathways & Professional Development

View Week 14 →
Week 15

Course Synthesis & Final Exam Review

Section 4 - SYNTHESIS

Topics

  • 15 Final-exam logistics: individualized scheduling, open-book/open-note policy, References & AI Use Declaration
  • 15 Two-part exam structure: common knowledge (Units 7–14) + individualized (Assignment 6 and Midterm Project)
  • 15 Unit ↔ Presentation map across the post-midterm material; study-guide walkthrough

Presentation: Pres 23 — Course Synthesis & Final Exam Review

Final Exam: Individualized 2h 25m windows, May 7–14 (9 AM or 1 PM)

View Week 15 →