Trustworthy Machine Learning
Spring Semester 2026, KAIST AI
1. Goal
- Students will be able to critically read, assess, and discuss research work in Trustworthy Machine Learning (TML).
- Students will gain the technical background to implement basic TML techniques in a deep learning framework.
- Students will be ready to conduct their own research in TML and make contributions to the research community.
2. Prerequisites
- Familiarity with Python and PyTorch coding.
- A pass grade from the Deep Learning Course (or equivalent).
- Basic knowledge of machine learning concepts.
- Basic maths: multivariate calculus, linear algebra, probability, statistics, and optimisation.
3. TML Book
Previous course materials are available as a book: https://trustworthyml.io/ (also on arXiv).
The book will be useful for the course. However, the course materials are updated yearly to stay aligned with the latest research, so it won’t cover new topics.
4. Schedule
| # | Date | Content | Quiz | Project |
|---|---|---|---|---|
| L1 | Mar 06 | Orientation (14:30 - 16:00) | — | Interest survey |
| L2 | Mar 13 | I. Human → AI: Generalisation via Data | Quiz 0 | — |
| L3 | Mar 20 | Modularity & Composition | — | Team formation due |
| L4 | Mar 27 | II. AI → Human: Training Data Attribution I | Quiz 1 | — |
| L5 | Apr 03 | Training Data Attribution II | — | — |
| L6 | Apr 10 | Explainability | — | — |
| L7 | Apr 17 | Uncertainty I | Quiz 2 | — |
| L8 | Apr 24 | Proposal presentations | — | Proposal due |
| L9 | May 01 | Uncertainty II | — | — |
| L10 | May 08 | III. Privacy & Security: Contextual Privacy | Quiz 3 | — |
| L11 | May 15 | Parametric Privacy | — | — |
| L12 | May 22 | Security & Jailbreaking | Quiz 4 | — |
| L13 | May 29 | IV. The Future: Agents & Synthesis | — | — |
| L14 | Jun 05 | Course Wrap-up | Quiz 5 | — |
| L15 | Jun 12 | Project Co-working | — | — |
| L16 | Jun 19 | Final Presentations | — | Final report due |
5. Assessment
5.1 Grading
| Component | Weight |
|---|---|
| Quizzes 1-5 (6% each) | 30% |
| Proposal presentation | 10% |
| Proposal report | 10% |
| Final presentation | 25% |
| Final report | 25% |
| Total | 100% |
Quiz 0 is a trial run and does not count towards the grade.
5.2 Quizzes
- Format: Google Forms, accessible via QR code in class (link shared on Slack simultaneously).
- Timing: Strict 10-minute window at the start of class.
- Structure: 3 questions covering material from previous lectures. Attending lectures is essential.
5.3 Team projects
- Team size: 3 students per team.
- Formation:
- Week 1: Interest survey.
- Week 3: Teams finalised.
- Deliverable: 4-page report + 10 min presentation.
- Peer evaluation: Mandatory form at the end. Distribute 100 points among your team members based on contribution. Unequal splits will affect individual grades.
Example project topics
Coming soon.
6. Generative AI Policies
Students may use generative AI tools (e.g. LLMs, VLMs, image generators). However, you are solely responsible for all outputs you submit. We will apply heavy penalties for:
- Hallucinated or factually incorrect outputs.
- Unsound or fabricated citations.
- Plagiarised materials.
- AI slop (low-effort, generic AI-generated content).
Severe cases may be reported to the university for disciplinary action.
You must be ready to answer clarification requests from the lecturer or tutors at any point. Inability to explain your own work will be treated as evidence of academic misconduct.
We do not tolerate very similar creative work among class members. AI tends to produce similar outputs across sessions and model families. Diversify your answers, especially for creative work. Suspicion of copied work will be penalised.
7. Communication & Logistics
Lecturer: Seong Joon Oh
Tutors: Bryan Truong, Seokwon Jung
When: Fridays 13:00-16:00
Where: 양재산학캠퍼스 대강의실 (Hybrid)
Email: stai.there@gmail.com for submissions, questions, and feedback.
Slack: Email us your name and preferred email address to be added. Use it for questions, announcements, and finding team members.