CSE 891: Adversarial Machine Learning

Basic information

  • Course time/location: Tu & Th 10:20 AM-11:40 AM EST; Instructor's zoom

  • Instructor: Prof. Sijia Liu

  • Instructor's office hour: General Q&A on Th 12-1 PM, or by appointment

  • Grading policy: Homework assignments, course presentations, final project

Course description

In recent years, adversarial ML is shown to be a key technique that leads to exciting breakthroughs and new challenges of many AI applications. In particular, adversarial robustness (centered at attack and defense) becomes an emerging topic to promote the trust of AI and enable a better understanding of the pros and cons of deep learning systems. More generally, the idea of learning with adversary is crucial for expanding the learning capability, ensuring trustworthy decision making, and enhancing generalizability of machine learning and data mining methods. Despite diverse adversarial concepts and applications, they share very similar learning, computation, and optimization foundations. Thus, the main course goal is to teach students how to adapt these fundamental techniques into different use cases of adversarial ML in computer vision, signal processing, data mining, and healthcare.