EECE 571J: Trustworthy Machine Learning (Spring 2025)

1. Overview

Machine Learning (ML) is a subset of artificial intelligence (AI) that enables systems to learn and improve from experience without being explicitly programmed. It involves using data and algorithms to allow computers to identify patterns, make decisions, or predict outcomes. ML now replaces humans at many critical decision points and is used in various applications, such as healthcare, finance, e-commerce, software and technology, education, and law. However, as ML systems increasingly influence high-stakes domains, ensuring their safety, security, and overall trustworthiness gains a high importance. This also explains a recent global push for regulating ML models all over the world, including in Canada.

This seminar-style course will explore different topics in emerging research areas related to the development of trustworthy ML systems, i.e., systems that are reliable, secure, explainable, ethical, and also compliant with existing law and regulations. Students will learn about quality assurance methods for ML systems, attacks against ML systems, defense techniques to mitigate such attacks, and ethical implications of using ML systems.

The course assumes students already have a basic understanding of machine learning. Most of the course readings will come from both seminal and recent papers in the field. Each student will read, summarize, and present several scientific papers, as well as propose, implement, and present their own original project. As such, the course will also focus on polishing the students’ research, development, communication, and technical presentation skills.

1.1 Learning Objectives

By the end of the course, students will learn:

• Foundations of Trustworthy Machine Learning;
• Quality assurance for ML systems;
• Robustness and reliability;
• Privacy in ML;
• Explainability and interpretability;
• Legal and ethical considerations;
• Efficient technical communication and presentation skills.

1.2 Course Prerequisites

This course does not have formal prerequisites. However, previous programming experience and a basic understanding of machine learning (equivalent to CPSC 340 or ELEC400M/ELEC571M ) are necessary.

2. Staff

Instructor	Prof. Julia Rubin Lectures: Thu. 2-5pm, CEME 1210 Office hours: Wed. 5-6pm, KAIS 4053 or by appointment (except January 29-->27, February 26-->24, April 2--> March 31)

3. Communication and Important Links

• Canvas is the main info hub. Course syllabus, reading material, project milestones, etc. are available on Canvas.
• Grades for the assignments will be posted throughout the term. Students are encouraged to check it frequently and let the staff know of any mistakes and inconsistencies.
• Course communication (questions, discussions, announcements, etc.) will be done via Piazza. Please enroll yourself!
• You can use private posts, if needed. Due to a high email volume, I will not be able to reply to emails but will prioritize and reply to Piazza posts.
• Like most online services, Piazza is hosted outside Canada. If you have issues using Piazza, please the instructor immediately and before the end of the first week of classes.

4. Topics and Tentative Schedule

5. Course Format

5.1 Reading Assignments

For weeks 3-5 and 8-11, students will read the assigned research papers (2 papers each week). Each student will submit a two-page summary of each paper that, on the first page, describes (a) the technical approach and (b) a critical review of the paper. On the second page, specify (c) how AI technology was used when working on the assignment.

For (a), describe, in bullet points, the input and outputs of the approach, its technical novelty, how the approach was evaluated, and what the results show. The description should take about 1/2 of the page. Points will be deduced for explanations that are not clear or not specific to the paper.

For (b), specify, in bullet points, 1-2 main strengths and weaknesses of the paper (not including those listed in the paper) and 1-2 suggestions for improvement and follow-up work. Points will be deduced for unclear statements, for listing non-original strength / weaknesses / suggestions, i.e., those stated in the paper, and for infeasible suggestions, which do not specify the execution plan. The description should take about 1/2 of the page and both (a) and (b) should be one page combined.

For (c), specify which AI technology, if any, was used to work on the assignment and how exactly these technology were used. Then, describe positives and negatives of using these technologies, i.e., when they were helpful - state how; when they were not helpful - state how and describe why, in your opinion, they were not helpful for your task. A template MS-Word document for paper summaries can be found here can be found here.

5.2 Paper Presentations

Each week, a student will present one of the assigned research papers to the class (two students each week). The student should motivate the need for the contribution made by the paper, put it in context of related work, summarize the proposed technique and its evaluation, discuss the strengths and weaknesses of the approach (beyond those listed in the paper), and lead the discussion on the paper. Depending on the number of course participants, each student will present 1-2 papers. Students do not need to submit summaries of the papers they present.

5.3 Project

The project will be performed by groups of 2-3 students. The scope of each group's project should match the number of students involved. The expectation for the project is to deepen the class’s understanding of topics related to trustworthy AI. That can include novel usage serious and identification of their pitfalls; novel applications of existing techniques to different scenarios; technical solutions; collection of statistical data on Trust ML issues and their impact on society, and novel literature reviews. Come to talk to the course instructor at least one week before the deadline if you want some ideas for inspiration!

There are five deliverables for the project. All reports should follow IEEE conference proceedings template, specified in the IEEE Conference Proceedings Formatting Guidelines (title in 24pt font and full text in 10pt type, LaTeX users must use \documentclass[10pt,conference]{IEEEtran} without including the compsoc or compsocconf options). 

• M0: Form groups and draft project ideas.
• M1: Project proposal
• The extended abstract should look as one of a finished paper and be up to 1 pages long. It should include (a) description of the problem solved in the project, (b) proposed technical approach, (c) evaluation method, (d) evaluation results (that you expect to show), and (e) implications of the results. On the second page, please include the timetable for completing the project and the planned role of each team member.
• Each group should set a meeting with the course instructor to discuss their project idea before submitting the proposal.
• M2: Report outline and intermediate status.
• The report should be up to 4 pages. The first 3 pages should include (a) an updated abstract (as in M1), (b) the structure of the final report: sections, subsections and a bullet point description of the intended content of each sub-section (including the results achieved so far). The last page should include (c) contribution of each team member, (d) plan to completion, possibly updated, and the planned role of each team member.
• M3: Demos and presentations in the course workshop. The format and the length of the presentation will be specified closer to the date.
• M4: Final project report.
• The report should be up to 8 pages and should be written in a typical paper format. Make sure to emphasize (a) the description of the problem solved in the project, (b) explicit statement of contribution and its novelty, with relation to existing work, (c) description of the technical approach, (d) evaluation and results, (e) lessons learned and future research directions. On the last page of the report, specify (f) the contribution of each team member to the work done in the project.

6. Grading

• Summaries of the assigned research papers and constructive points for discussion – 15%
• Presentation of 1-2 research papers in class – 25%
• Project – 55%, specifically:
  • M1: Project proposal – 10% (only if final report is submitted)
  • M2: Report outline and intermediate status – 5% (only if final report is submitted)
  • M3: Presentation slides + project demo and presentation – 15%
  • M4: Final project report – 25%
• Constructive participation in class discussions – 5%

7. Absence and Late Deliverables

• This course is based on group discussions. As such, the attendance in lectures is mandatory.
• If you are sick or have another justified reason to miss a class, please notify the instructor ahead of time (via Piazza).
• Late deliverables:
• Each team is given another 3 grace days per term in total, which can be used for milestones M1, M2, and M4.
• You can use the grace days as you wish, i.e., all four days on one deliverable, distribute across deliverables, etc.
• Grace days are counted as integers, i.e., if you are one hour late, that counts as one grace day.
• Once all your grace days are all used, late submissions will receive a grade of zero.

8. Use of AI Technology

The use of AI technology (such as ChatGPT and CoPilot) is allowed in this course, but all usages should be explicitly declared and documented. Students are ultimately accountable for the work they submit. Unreported and undocumented use is considered academic integrity violation and will be treated accordingly. As such, throughout the course, students will document and critically analyze their usage of AI technology, identifying its strengths and weaknesses. The analysis must be submitted as part of the assignment and will be graded.

9. Academic Integrity

The academic enterprise is founded on honesty, civility, and integrity. As members of this enterprise, all students are expected to know, understand, and follow the codes of conduct regarding academic integrity. At the most basic level, this means submitting only original work done by you and acknowledging all sources of information or ideas and attributing them to others as required. This also means you should not cheat, copy, or mislead others about what is your work. Violations of academic integrity (i.e., misconduct) lead to the breakdown of the academic enterprise, and therefore serious consequences arise and harsh sanctions are imposed. For example, incidences of plagiarism or cheating may result in a mark of zero on the assignment or exam and more serious consequences may apply if the matter is referred to the President’s Advisory Committee on Student Discipline. Careful records are kept in order to monitor and prevent recurrences.

For more information, see here.

10. APSC and UBC-wide Policies

10.1 Academic Concession

The University is committed to supporting students in their academic pursuits. Students may request academic concession in circumstances that may adversely affect their attendance or performance in a course or program. Students who intend to, or who as a result of circumstance must, request academic concession must notify their instructor, dean, or director as specified in the link below. https://www.calendar.ubc.ca/vancouver/index.cfm?tree=3,329,0,0 Students seeking academic concession due to absence from the final exam for any reason must apply to Engineering Academic Services (EAS) within 72 hours of the missed exam. This is a standard practice for all final examinations at UBC. For more information, see: https://academicservices.engineering.ubc.ca/exams-grades/academic-concession/

10.2 Health and Wellness

UBC provides resources to support student learning and to maintain healthy lifestyles, while recognizing that challenges and crises can arise for students. There are resources in ECE and at UBC where students can find help and support, including wellness, equity, inclusion and indigeneity, resources for survivors of sexual violence, and health. Some frequently used resources are as follows:

• ECE Wellness Hub: https://ece.ubc.ca/student-life/student-wellness/
• ECE has an EDI.I committee whose goals are to improve equity, diversity and inclusion in the ECE Department, and support the UBC Indigenous Strategic Plan. The committee welcomes feedback from all students, and can be contacted by emailing help@ece.ubc.ca.
• Central resource for supporting student success (medical and crisis support, Centre for Accessibility, and support for survivors of sexual violence): https://senate.ubc.ca/vancouver/policies-resources-support-student-success/
• UBC Office of the Ombudsperson for Students: https://ombudsoffice.ubc.ca/how-we-can-help/

UBC values respect for the person and ideas of all members of the academic community. Harassment and discrimination are not tolerated nor is suppression of academic freedom. UBC provides appropriate accommodation for students with disabilities and for religious, spiritual and cultural observances. UBC values academic honesty and students are expected to acknowledge the ideas generated by others and to uphold the highest academic standards in all of their actions. Details of UBC’s respectful environment policies, which all students, staff and faculty are expected to follow, can be found here: https://hr.ubc.ca/working-ubc/respectful-environment

10.3 University Policies

UBC provides resources to support student learning and to maintain healthy lifestyles but recognizes that sometimes crises arise and so there are additional resources to access including those for survivors of sexual violence. UBC values respect for the person and ideas of all members of the academic community. Harassment and discrimination are not tolerated nor is suppression of academic freedom. UBC provides appropriate accommodation for students with disabilities and for religious, spiritual and cultural observances. UBC values academic honesty and students are expected to acknowledge the ideas generated by others and to uphold the highest academic standards in all of their actions. Details of the policies and how to access support are available here