Adversarial Machine Learning


Title: Adversarial Machine Learning
Date: Monday, July 16, 2018
Time: 12:00 PM Eastern Daylight Time
Duration: 1 hour

SPEAKER: Ian Goodfellow, Staff Research Scientist, Google Brain

Webinar Registration Link (free)
Introduction to Deep Learning Business Applications for Developers: From Conversational Bots in Customer Service to Medical Image Processing (Skillsoft book, free for ACM Members)
Feature Engineering for Machine Learning and Data Analytics (Skillsoft book, free for ACM Members)
Pro Deep Learning with TensorFlow: A Mathematical Approach to Advanced Artificial Intelligence in Python (Skillsoft book, free for ACM Members)
Ubiquitous Machine Learning and Its Applications (Skillsoft book, free for ACM Members)
Practical Machine Learning with Python: A Problem-Solver’s Guide to Building Real-World Intelligent Systems (Skillsoft book, free for ACM Members)
Google Cloud Big Data and Machine Learning (Skillsoft course, free for ACM Members)
Machine Learning and Security (Safaribook, free for ACM Members)
LEARNING PATH: Deep Learning with TensorFlow: Applications of Deep Neural Networks to Machine Learning Tasks (Safari Videos, free for ACM Members)
LEARNING PATH: Deep Learning for Natural Language Processing: Applications of Deep Neural Networks to Machine Learning Tasks (Safari Videos, free for ACM Members)

Is there a tech support site where we can report issues with the webinars?

Can adversarial machine learning be used to defend against adversarial examples?


Hi Ian,
I’m researching at the cross section of AI and Law and have a few questions for which I would appreciate your thoughts. These questions are not exactly about Deep Learning but at the fundamentals of Deep Neural Networks. Questions:

  1. Do we have the ability/ need to interpret the the synoptic weights in Neural Networks? To a layman as well as to expert machine learning researchers, neural network weight matrices don’t convey any meaningful information. I believe there is some ongoing research in algebraic topology to understand what mathematical spaces these un-interpretable weight matrices occupy. What is your intuitive understanding on the interpretability of Neural weights (connection between the neurons)? The reason for asking this question is to understand the mutation of input till the predicted output (Since, neural net weights don’t convey any actionable information on the influence of input predictors on the outcome)
  2. Is it time again (a very strong debate around this topic was active in 1990s) that we ask for copyright on Neural weights (Does Google copyright the neural weights of its ML platforms)? One of the secret saucages behind how effective a Deep neural network is the weights arrived after thousands of hours worth of training. Seeing the time and investment that went behind arriving on those weighted numbers, it is indeed very valuable. Your thoughts?


Hi Ian,

I am trying to use GANs for generating medical data. I am planning to give correlation between features as an extra information to the GAN (think of it as a knowledge based model) but not sure how to incorporate explicit correlation based loss along with the original loss function. Any tips and insights?


What encouraged you to pursue research in this area? what were the early signals? Can you share some examples?Thanks!


If tech support is on here , the webinar is not working. Specifically, I try to register, hit submit button and nothing. I tested another webinar and it works just fine, so it is not my setup.


I’m having the same problem, did you find out a solution?


I believe that @Negar_Rostamzadeh maybe will be able to help since she was the moderator of this ACM Webinar. Negar, this ACM Webinar is no longer viewable, me and @Willy_Rempel have tried to register to see the archived webinar but it does not work (but it works for other past webinars). Do you know who can fix it?


I just checked the help link, there is a test to check for cookies, blockers, etc.
My system checked out okay.

I also cleared cookies and tried again. Still nothing.


Link now fixed. Apologies for the inconvenience.


Fixed link:


Thanks, much appreciated