CS 391B: Responsible AI, Fall 2025

Course Description

Technological advances in how information is generated, collected, managed, and analyzed raise a variety of societal concerns. This course will explore how to use mathematical methods to articulate some of these challenges formally, reason about them rigorously, and design algorithms to mitigate them. Potential topics include data privacy, fairness in algorithmic learning and decision-making, evaluation and interpretation of complex machine learning models, feedback loops in data-driven systems, and strategic behavior. An emphasis will be placed on understanding the challenges arising from modern machine learning, such as through large language models.

The course, which is aimed at advanced undergraduates in computer science, data science, ECE, or statistics, will engage with both technical components of the problem area (involving programming and theoretical problems) as well as questions in policy and ethics (involving reading, discussing, and writing about papers from those areas).


Instructor:   Mark Bun, mbun [at] bu [dot] edu
Instr. Office Hours:   Tue 3:30-4:30 PM (CDS 1021)
    Wed 4-6 PM (CDS 1021)
     
Teaching Fellow:   Mandar Juvekar, mandarj [at] bu [dot] edu
Mandar's Office Hours:   Mon 9-10 AM (CDS 10th Floor Yellow Lounge)
    Thu 12:45-1:45 PM (CDS 10th Floor Yellow Lounge)
     
Class Times:   Tue, Thu 2:00-3:15 PM (PSY 212)
Discussion Sections:   Mon 12:20-1:10 PM (CDS 701)
  Mon 1:25-2:15 PM (CDS 701)

Important Links

Course Website: https://cs-people.bu.edu/mbun/courses/391_F25. The website contains the course syllabus, schedule with assigned readings, homework assignments, and other course materials.

Piazza: https://piazza.com/bu/fall2025/cs391b. All class announcements will be made through Piazza, so please set your notifications appropriately. You can also find course handouts and homework/test solutions there. Please post questions about the course material to Piazza instead of emailing the course staff directly. It is likely that other students will have the same questions as you and may be able to provide answers in a more timely fashion. Active participation on Piazza may add extra points to your participation grade.

Gradescope: https://gradescope.com. Sign up for a student account on Gradescope using your BU email address. The entry code for the course is 6KYJPK. Homework assignments are to be submitted to Gradescope in PDF format.


Prerequisites

Probability (e.g., CS 237 or DS 122), algorithms (e.g., CS 330 or DS 320), and the basics of machine learning (e.g., CS 365 or DS 340). Additional background in AI, machine learning, or statistics is helpful but not required. Students from programs outside CS and DS are welcome but should contact the instructors regarding prerequisites.

List of Potential Topics


(Perpetually Tentative) Schedule

Date Topics Reading/Reference Handouts/Assignments
Tue 9/2 Welcome, introduction, supervised learning basics [BHN] pp.44-51, [SS] Ch. 2
Thu 9/4 Sources of bias in data and models, philosophical foundations of fairness, start group fairness [BHN] Ch. 1, pp.52-63, 76-80; Machine Bias + analysis
Optional: Fairness in Philosophy
Tue 9/9 Group fairness and how to achieve it [BHN] pp.52-63, 67-71, 81-87, 92-94, 97-101
Equality of Opportunity in Supervised Learning
Thu 9/11 Group fairness tradeoffs [BHN] pp.63-67
Optional: What Should We Do When Our Ideas of Fairness Conflict?
Tue 9/16 Individual fairness Fairness through Awareness, [BHN] pp.94-97
Thu 9/18 Multi-group fairness Calibration for the (Computationally-Identifiable) Masses
Tue 9/23 Fairness and causality [BHN] pp.104-121
Thu 9/25 Counterfactual fairness [BHN] pp. 121-131
Counterfactual Fairness
HW 1 due
Tue 9/30 Intro to interpretability [Mol] Ch 1-4
Towards a Rigorous Science of Interpretable Machine Learning
Thu 10/2 AI in government, linear and logistic models [Mol] Ch 6-7
Tue 10/7 Decision rules, sets, lists, trees [Mol] Ch 9-10
Thu 10/9 Local model-agnostic explanations [Mol] Ch 12-14, 17-18
Tue 10/14 NO CLASS — Substitute Monday for Indigenous People's Day
Thu 10/16 Counterfactual explanations, global model-agnostic explanations [Mol] Ch 15, 19-24 HW 2 due
Tue 10/21 Test Review
Thu 10/23 Test 1
Tue 10/28 Interpreting convolutional networks [Mol] Ch 27-28
Zoom In: An Introduction to Circuits
Thu 10/30 Interpreting transformers A Mathematical Framework for Transformer Circuits
In-context Learning and Induction Heads
Tue 11/4 Induction heads, locating facts in LLMs In-context Learning and Induction Heads
ROME: Locating and Editing Factual Associations in GPT
Thu 11/6 Activation steering Steering Language Models with Activation Engineering
Tue 11/11 Emergent misalignment Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs
Thu 11/13 Alignment via reinforcement learning Training Language Models to Follow Instructions with Human Feedback
Tue 11/18 Student presentations (HW 3)
Thu 11/20 Student presentations (HW 3)
Tue 11/25 Attacks and memorization Exposed! A Survey of Attacks on Private Data
Extracting Training Data from Large Language Models
Thu 11/27 NO CLASS — Thanksgiving
Tue 12/2 Differential privacy basics [DR] Ch 1, 2, 3.1-3.3, 3.5
Thu 12/4 Differentially private algorithms [DR] Ch 3.3-3.5
Tue 12/9 Private model training Differentially Private Empirical Risk Minimization HW 4 due
Tue 12/16 Test 2 (3-5PM), PSY 212

Texts and References

You do not need to buy a textbook for this class. Required reading will come from sources that are either freely available on the web or accessible using your BU institutional login. The abbreviated references in the schedule are to the following textbooks and monographs.

[BHN] Solon Barocas, Moritz Hardt, and Arvind Narayanan. Fairness and Machine Learning: Limitations and Opportunities. [link]
[DR] Cynthia Dwork and Aaron Roth. The Algorithmic Foundations of Differential Privacy. [link]
[FV] Ferdinando Fioretto and Pascal Van Hentenryck (ed.). Differential Privacy in Artificial Intelligence: From Theory to Practice. [link]
[Mol] Christoph Molnar. Interpretable Machine Learning: A Guide to Making Black Box Models Explainable. [link]
[MRT] Mehryar Mohri, Afhin Rostamizadeh, and Ameet Talwalkar. Foundations of Machine Learning. [PDF and e-book]
[SS] Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. [PDF]

Evaluation

Your grade in the course will be determined by homework assignments, two in-class tests, and class participation.

Homework (55%)

There will be roughly four homework assignments, tentatively due 9/25, 10/16, 11/13, and 12/9, each at 11:59PM. Assignments will include a mix of mathematical problem-solving, programming, and sociotechnical writing. Some homework problems will be designed to be challenging or open-ended. You will want to start early to give yourself time to think deeply about the problems. Even so, do not be discouraged if you cannot completely solve all of the problems, and we welcome well-reasoned partial ideas toward solutions. We will aim to turn around homework solutions shortly after each due date, so we cannot accept late assignments without prior arrangement due to exceptional circumstances.

You are allowed, and indeed encouraged, to collaborate with other students on solving most of the homework problems. However, you must write the solutions independently in your own words. Details of the collaboration policy may be found below under the header "Collaboration Policy."

You may want to use LaTeX to typeset your homework solutions. LaTeX is the standard document preparation system used in the mathematical sciences. Using LaTeX makes it easier for you to revise and edit your solutions and for us to read them, so you will never lose points for illegibility.

My preferred LaTeX editors are TexShop for Mac and TexStudio for Windows. If you would like to give LaTeX a try on the web without installing anything on your computer, Overleaf is a good option.

Not so short intro to LaTeX. A LaTeX tutorial.

Test 1: 15%, Test 2: 15%

Two in-class tests are scheduled for Thursday, October 23 and (tentatively) Tuesday, December 16 during our final exam slot. (Please wait until the official University final exam schedule is finalized before making your end-of-semester travel plans.) Each test will cover roughly half of the course content. Test 2 is not intended to be cumulative.

You may bring one double-sided 8.5" x 11" sheet of notes to each test. Note sheets may be either handwritten or typeset. You may not use any other aids during the exam, including but not limited to books, lecture notes, calculators, phones, or laptops.

Class Participation (15%)

Your active participation in class and in discussion section activities is an essential part of your learning and will make it much more enjoyable for everyone. You can also earn participation credit by asking thoughtful questions on Piazza or during office hours. Midway through the semester, I will send you an indication on how your participation in class is going.


Collaboration Policy

You may verbally collaborate on homework problems with up to 3 students currently enrolled in the course. However, you must write your solutions independently in your own words, and understand what you are writing well enough to explain your solutions to the course staff if asked. You must also list the names of everyone with whom you collaborated on your assignment.

You may use external resources such as textbooks, lecture notes, research articles, blog posts, and videos to supplement your general understanding of the course topics or conduct research as needed. You must cite your sources for any ideas or auxiliary materials (e.g., datasets) you submit that are not your own. You may also get help from anyone on debugging LaTeX or other issues that are clearly more general than the scope of the course.

You may not look up answers to homework problems in the published literature, on the web, or using generative AI. You may not submit work that you did not write yourself. You may not share written work with anyone else.

The use of generative AI tools like ChatGPT is permitted as long as it conforms to the policies above. That is, you may use them for general research (as you might use a search engine), but you may not prompt them to answer specific homework problems and you may not misrepresent their output as if it were your own work.

If you are uncertain as to whether a particular kind of interaction with someone else constitutes illicit collaboration or academic dishonesty, please ask the instructor before taking any action that might violate the rules. If you can’t reach the instructor in time, cite your sources and include a clear explanation of what happened on your submission.


Additional Course Policies

Academic Conduct

All Boston University students are expected to maintain high standards of academic honesty and integrity. It is your responsibility to be familiar with the Academic Conduct Code, which describes the ethical standards to which BU students are expected to adhere and students’ rights and responsibilities as members of BU’s learning community. All instances of cheating, plagiarism, and other forms of academic misconduct will be addressed in accordance with this policy. Penalties for academic misconduct can range from failing an assignment or course to suspension or expulsion from the university.

https://www.bu.edu/academics/policies/academic-conduct-code/
http://www.bu.edu/cas/current-students/phd-mfa-students/academic-policies-and-conduct-code/

Regrade Policy

If you find a mistake in the grading, Gradescope has a feature built in for requesting regrades. We will accept regrade requests for up to one week after each homework assignment or test is returned. Before submitting a regrade request, please make sure you have read and understood the distributed solutions. Regrade requests must point out specific factual errors in how the grader interpreted your solution. To ensure grading consistency, we cannot accommodate requests based on disagreements about how much a given mistake should correspond to a point value.

Attendance Policy

Students are expected to attend each class session unless they have a valid reason for being absent. If you must miss class due to illness or another reason, please notify the instructor as soon as possible, ideally before the absence.

https://www.bu.edu/academics/policies/attendance/

Absence Due to Religious Observance

If you must miss class due to religious observance, you will not be penalized for that absence and you will receive a reasonable opportunity to make up any work or examinations that you may miss. Please notify the instructor of absences for religious observance as soon as possible, ideally before the absence.

https://www.bu.edu/academics/policies/absence-for-religious-reasons/

Bereavement

In the event of the death of an immediate family member, you should notify your advisor, who will help you coordinate your leave. You will be automatically granted five weekdays of leave, and if necessary, you advisor will help you to petition the Dean for additional leave time. You may also request a leave of absence due to bereavement. Please contact your advisor, who will help you with the process.

https://www.bu.edu/academics/policies/student-bereavement/

Disability Services

Students with documented disabilities, including learning disabilities, may be entitled to accommodations intended to ensure that they have integrated and equal access to the academic, social, cultural, and recreational programs the university offers. Accommodations may include, but are not limited to, additional time on tests, staggered homework assignments, note-taking assistance. If you believe you should receive accommodations, please contact the Office of Disability Services to discuss your situation. This office can give you a letter that you can share with instructors of your classes outlining the accommodations you should receive. The letter will not contain any information about the reason for the accommodations.

If you already have a letter of accommodation, you are encouraged to share it with your instructor as soon as possible.

Disability & Access Services
25 Buick Street, Suite 300
617-353-3658
access@bu.edu
http://www.bu.edu/disability/

Grade Grievances

If you feel that you have received an arbitrary grade in a course, you should attempt to meet with the grader before filing a formal appeal. If the student and the instructor are unable to arrive at a mutually agreeable solution, the student may file a formal appeal with the chair. This process must begin within six weeks of the grade posting. To understand how an “arbitrary grade” is defined, please explore the following link.

https://www.bu.edu/academics/policies/policy-on-grade-grievances-for-undergraduate-students-in-boston-university-courses/

Incomplete Grades

An incomplete grade (I) is used only when the student has conferred with the instructor prior to the submission of grades and offered acceptable reasons for the incomplete work. If you wish to take an incomplete in this class, please contact the instructor as soon as possible but certainly before the submission of final grades. To receive an incomplete, you and your instructor must both sign an “Incomplete Grade Report” specifying the terms under which you will complete the class.

https://www.bu.edu/academics/policies/incomplete-coursework/

Student Health Services

Offers an array of health services to students, including wellness education and mental health services (behavioral medicine).

http://www.bu.edu/shs/
http://www.bu.edu/shs/wellness/
http://www.bu.edu/shs/behavioral/index.shtml

Medical Leave of Absence

If you must take a leave of absence for medical reasons and are seeking to re-enroll, documentation must be provided to Student Health Services so that you may re-enroll. To take a medical leave, please talk with SHS and your advisor, so that they may assist you in taking the best course of action for a successful return.

http://www.bu.edu/usc/leaveandwithdrawal/arranging/
http://www.bu.edu/academics/policies/withdrawal-leave-of-absence-and-reinstatement/

ISSO

The International Students & Scholars Office is committed to helping international students integrate into the Boston University community, as well as answering and questions and facilitating any inquiries about documentation and visas.

https://www.bu.edu/isso/