This course focuses on a range of quality-issue of AI systems, such as robustness, backdoor-freeness, fairness, privacy and interpretability. What is covered include systematic ways of evaluating whether a given AI system (typically in the form of a neural network) satisfies different quality metrics and how to improve the system’s robustness, backdoor-freeness, fairness, privacy and interpretability.
This course is a part of the MITB program at SCIS, Singapore Management University.
Agenda
Week 1: AI Security Problems, and AI Analysis vs Program Analysis
Week 2: AI Robustness
Week 3: Improving AI Robustness
Week 4: AI Backdoors
Week 5: Mitigating AI Backdoors
Week 6: AI Fairness
Week 7: Improving AI Fairness
Week 8: AI Privacy
Week 9: Improving AI Privacy
Week 10: AI Interpretability
This course comes with many in-class exericses and programming examples, which can be found at this repository. This repository is maintained by Pham Hong Long.