CS 498 LB1 - Special Topics - Trustworthy Machine Learning
Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: 1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.
Although machine learning has been widely applied to various applications, the security and privacy vulnerabilities of the models and algorithms require more careful exploration to develop trustworthy machine learning systems. This course will first discuss the foundation of machine learning, optimization algorithms, and deep learning models; and then introduce different attack approaches against various learning models. We will later discuss potential defense strategies and principles against different attacks, as well as how to protect data privacy to improve data utility for large scale learning systems in adversarial environments. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/CSregister
Option 1Number of Required Visit(s): 0
Course Level: Graduate