CS 502 Directed Studies: Adversarial Machine Learning

CS 502 Directed Studies: Adversarial

Machine Learning

Dr. Alex Vakanski

Lecture 1

CS 502, Fall 2020

Introduction to Adversarial Machine Learning

2

Lecture Outline

CS 502, Fall 2020

? Machine Learning (ML) ? Adversarial ML (AML)

? Adversarial examples

? Attack taxonomy ? Common adversarial attacks

? Noise, semantic attack, FGSM, BIM, PGD, DeepFool, CW attack

? Defense against adversarial attacks

? Adversarial training, random resizing and padding, detect adversarial examples

? Conclusion ? References ? Other AML resources

3

Machine Learning (ML)

CS 502, Fall 2020

? ML tasks

? Supervised, unsupervised, semi-supervised, self-supervised, meta learning, reinforcement learning

? Data collection and preprocessing

? Sensors, cameras, I/O devices, etc.

? Apply a ML algorithm

? Training phase: learn ML model (parameter learning, hyperparameter tuning)

? Testing phase (inference): predict on unseen data

Slide credit: Binghui Wang: Adversarial Machine Learning -- An Introduction

4

ML is Ubiquitous

CS 502, Fall 2020

Healthcare

Picture from: He Xiaoyi ? Adversarial Machine Learning

5

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download