Completed
Overview
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Explaining and Harnessing Adversarial Examples in Machine Learning - Spring 2021
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Overview
- 3 Paper History and Authors
- 4 Motivation
- 5 Adversarial Examples for Linear Models
- 6 Adversarial Example for Non-Linear Models • Is it applicable for nonlinear models?
- 7 Summarizing FGSM
- 8 Experimental Results ► GSM band attack on Neural network with different activation function
- 9 Adversarial Training (AT)
- 10 FGSM Attack to a Logistic Regression Model
- 11 Adversarial Training for Logistic Regression Model
- 12 L1 regularization for Logistic Regression Model • To prevent the overfitting problem
- 13 Adversarial Training vs L1 weight decay • Training maxout networks on MNIST . Good results using adversarial training with = 0.25
- 14 Adversarial Training of DNN
- 15 Adversarial Trained Model
- 16 Other Considerations
- 17 Why Do Adversarial Examples Generalize?
- 18 Generalization of Adversarial Examples
- 19 Alternative Hypothesis
- 20 Strengths
- 21 Weaknesses
- 22 Summary
