Completed
ML via Adversarial Robustness Lens
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
A New Perspective on Adversarial Perturbations
Automatically move to the next video in the Classroom when playback concludes
- 1 Why do we love deep learning?
- 2 Key Problem: Adversarial Perturbations
- 3 ML via Adversarial Robustness Lens
- 4 Human Perspective
- 5 ML Perspective
- 6 A Simple Experiment
- 7 The Robust Features Model
- 8 The Simple Experiment: A Second Look
- 9 Human vs ML Model Priors
- 10 New capability: Robustification
- 11 A Natural Consequence: Transferability
- 12 The Role of Robust Training
- 13 New Take on Randomized Smoothing
- 14 Robustness and Data Efficiency
- 15 A Simple Theoretical Setting: Max Likelihood Gaussian Classification
- 16 Robustness + Perception Alignment
- 17 Robustness + CV Applications
- 18 Adversarial examples arise from non-robust features in the data