Главная
Study mode:
on
1
Intro
2
I.I.D. Machine Learning
3
Attacks on the machine learning pipeline
4
Define a game
5
Fifty Shades of Gray Box Attacks
6
Transfer Attack
7
Norm Balls: A Toy Game
8
Tradeoff
9
Gradient Masking
10
Pipeline of Defense Failures
11
Adversarial Logit Pairing (ALP)
12
Future Directions: Indirect Methods
13
Future Directions: Better Attack Models
14
Some Non-Security Reasons to Study Adversarial Examples
15
Clever Hans
Description:
Explore a comprehensive keynote address on adversarial example research in machine learning and cybersecurity. Delve into the intricacies of defending against attacks on the machine learning pipeline, including transfer attacks, gradient masking, and norm ball scenarios. Examine the concept of adversarial logit pairing (ALP) and investigate future research directions in indirect methods and improved attack models. Gain insights into non-security applications of adversarial examples and the fascinating "Clever Hans" phenomenon. Learn from Ian Goodfellow's expertise as he presents at the 1st Deep Learning and Security Workshop during the 2018 IEEE Symposium on Security & Privacy in San Francisco.

Defense Against the Dark Arts

IEEE
Add to list
0:00 / 0:00