The course aims to teach learners how to secure neural networks against adversarial attacks in the field of Machine Learning. The course covers topics such as adversarial attacks, defenses, certified robustness, and other methods like differential privacy. The teaching method includes lectures on various domains affected by adversarial attacks, examples of attacks, and strategies for defense. This course is intended for researchers and developers looking to enhance the security of their machine learning models.
Getting Robust - Securing Neural Networks Against Adversarial Attacks
University of Melbourne via YouTube
Overview
Syllabus
Introduction
Meet Andrew
Deep Learning Applications
Adversarial Learning
Deanonymization
Tay
Simon Wecker
What is an adversarial attack
Examples of adversarial attacks
Why adversarial attacks exist
Accuracy
Accuracy Robustness
Adversarial Attacks
Adversarial Defense
Certified Robustness
Differential Privacy
Differential Privacy Equation
Other Methods
Example
Polytope Bounding
Test Time Samples
Training Time Attacks
Conclusion
Taught by
The University of Melbourne
