Course Syllabus

This course covers the principles and practices of the interactions between machine learning and security, including examining the security properties of modern ML models and applying ML to address software and system security problems. The course begins with an introduction to the foundations of ML and modern deep learning models, such as transformers, and their applications in solving security problems. The later modules focus on crucial security properties of ML models, specifically adversarial robustness and backdoor threats. Hands-on coding assignments using popular ML libraries like PyTorch are included to provide students with practical experience. Additionally, the course aims to inspire the exploration of advanced challenges in the field by reviewing recent papers from top-tier conferences. By the end of the course, students will be equipped to evaluate ML systems in academic and commercial security contexts and will have foundational skills in security and ML research.

At the end of this course, students will be able to:

• Understand modern ML algorithms
• Gain knowledge in applying ML to security and exploring the security of ML
• Obtain foundational skills in security and ML research

There is no official textbook for the class. Slides will be provided and reading materials for each topic will be assigned from the following references:

Recommended Texts

• Pattern Recognition and Machine Learning, Christopher Bishop, Springer (2006)
• Machine Learning: A Probabilistic Perspective, Kevin P Murphy, MIT Press (2012)
• Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT press (2016)

Preferred Contact Methods

The easiest way to contact your instructor directly is to use the Inbox, located in the far left Canvas menu.

You can also contact your instructor in the following way:

• guanhong.tao@utah.edu

Office Hours

The instructor will hold office hours according to the following schedule:

Day: Tuesday

Time: 5PM - 6PM

Your performance in this course will be evaluated by:

• 10% Attendance & In-class Quizzes
• 30% Homework (3 coding assignments)
• 20% Paper Review
• 20% Midterm Exam
• 20% Final Exam

Formating

Each homework write-up must be neatly typeset as a PDF document. You can use LaTeX or any other system that produces typesetting of equal quality and legibility (especially for mathematical symbols and expressions). Please write your solutions as succinctly as possible while including all the necessary details. Ensure that the following appear at the top of the first page of the write-up: your name, your UID, and the ID’s of any students with whom you discussed the assignment. Submit your write-up as a single PDF file and corresponding code implementations (if any) on Canvas by 11:59 PM of the due date. It is your responsibility to ensure that the submission is successfully received by Canvas.

All assignments, unless otherwise announced, must be submitted to the designated area of
Canvas. Do not submit assignments via email.

Due Date Time

Assignments will be accepted up until 11:59 PM on the due date. The score for late homework is 0. Exceptions will be made in case of serious illness or bereavement. If a student has a planned absence from a class when an exam will be given, the student should make arrangements before the planned absence to take the exam early or take a makeup exam after returning to campus.

Grade Disputes

Feedback on graded material will be posted on Canvas in as timely a manner as possible. Once feedback for a graded assignment is posted, you will have 1 week from the posting date to dispute a grade. No re-grade requests will be honored after 1 week from posting feedback. Grade changes will not be made at the end of the semester.

Collaboration Policy

You are encouraged to discuss course materials and reading assignments, and homework assignments with each other in small groups (two to three people). You must list all discussants in your homework write-up. Discussion about homework assignments may include brainstorming and verbally discussing possible solution approaches, but must not go as far as one person telling others how to solve a problem. In addition, you must write-up your solutions by yourself, and you may not look at another student’s homework write-up/solutions (whether partial or complete).

There is a total of 3 days of grace period available for late submissions across all assignments. You may use this grace period for any assignment. However, please note that the grace period is cumulative. Once the 3-day grace period has been fully used, any further late submissions will receive a score of 0, in accordance with the assignment policy.

Grades will be determined based on correctness and relevance to the assignments and questions. Pay close attention to the instructions and rubrics provided for each assignment/task.

Extra credit opportunities may be available throughout the course. These will be clearly communicated and typically involve additional research, attending relevant events, or completing supplementary assignments. Extra credit can contribute up to 5% additional points to the final grade.

Grading scale

Disclaimer

Accommodations will be considered on an individual basis and may require documentation.

Please contact your instructor as soon as possible (preferably shortly before the semester begins) to request accommodations of any kind.

Content Warnings

Please be aware that some materials and discussions within this course may contain challenging content. Your instructor may choose to notify students of potentially difficult content (e.g. explicit language, graphic images, violent themes, etc.) throughout the course.

If there are specific subjects that you need advanced notice for, please contact your instructor at the beginning of the semester.

Extreme personal circumstances

Please contact your instructor as soon as possible if an extreme personal circumstance
(hospitalization, death of a close relative, natural disaster, etc.) is interfering with your ability to
complete your work.

Religious Practice

To request an accommodation for religious practices, contact your instructor at the beginning of the semester.

Active Duty Military

If you are a student on active duty with the military and experience issues that prevent you from participating in the course because of deployment or service responsibilities, contact your instructor as soon as possible to discuss appropriate accommodations.

Disability Access

All written information in this course can be made available in an alternative format with prior notification to the Center for Disability Services (CDS). CDS will work with you and the instructor to make arrangements for accommodations. Prior notice is appreciated. To read the full accommodations policy for the University of Utah, please see Section Q of the Instruction & Evaluation regulations.

If you will need accommodations in this class, contact:

Center for Disability Services
  801-581-5020
  disability.utah.edu
  162 Union Building
    200 S. Central Campus Dr.
     Salt Lake City, UT 84112

This syllabus is not a contract. It is meant to serve as an outline and guide for your course. Please note that your instructor may modify it to accommodate the needs of your class.

You will be notified of any changes to the Syllabus.