COSC 89.40 Topics in Adversarial Machine Learning

This seminar surveys the security and privacy of machine learning systems, with a focus on classical (non-generative) ML and deep learning models deployed in adversarial environments. Students will read and discuss foundational and recent research on evasion attacks (adversarial examples), data poisoning and backdoors, model extraction and stealing, membership-inference and privacy leakage, certified and empirical defenses, and the security of federated learning. The course emphasizes how attackers reason about ML pipelines end-to-end—from training data and model internals to deployment APIs and physical-world sensors—and how defenders can build models that are robust, private, and accountable.

The class operates as a student-led research seminar. Weekly meetings center on reading and discussing recent papers from the top security venues (IEEE S&P / Oakland, USENIX Security, CCS, NDSS) and the top machine learning venues (NeurIPS, ICML, ICLR). Short instructor lectures provide methodological context (threat models, optimization-based attacks, robust optimization, differential privacy). Evaluation is based on discussion leadership and participation, weekly reflections, and a semester project with defined milestones that extends, critiques, or applies one of the covered research areas.

Degree Requirement Attributes

Dist:TAS

The Timetable of Class Meetings contains the most up-to-date information about a course. It includes not only the meeting time and instructor, but also its official distributive and/or world culture designation. This information supersedes any information you may see elsewhere, to include what may appear in this ORC/Catalog or on a department/program website. Note that course attributes may change term to term therefore those in effect are those (only) during the term in which you enroll in the course.

Department-Specific Course Categories

Computer Science