Trustworthy
Machine Learning
Lecture slides
15–22- Lecture 15
Introduction to Adversarial Attacks
Open slides - Lecture 16
Generating Adversarial Examples
Open slides - Lecture 17
Generating Adversarial Examples (Part II)
Open slides - Lecture 18
Black Box Attacks
Open slides - Lecture 19
Training-Time Attacks: Poisoning and Backdoors
Open slides - Lecture 20
Defences I: Test-Time Attacks
Open slides - Lecture 21
Poisoning Defences and the Public Good
Open slides - Lecture 22
Bias and Fairness in Machine Learning
Open slides