[Colloquium] REMINDER: 10/26 Machine Learning Seminar Series: Thomas Goldstein, University of Maryland

[Mary Marre via Colloquium]

*When:         *Friday October 26, 11am-12pm

*Where:        *Room 526, TTIC 6045 S Kenwood Avenue

*Who:           *Thomas Goldstein, University of Maryland

*Title:           *A New Take on Adversarial Examples

*Abstract: *Neural networks perform extremely well at object recognition
tasks, sometimes even meeting or exceeding human performance.  However,
neural networks have recently been shown to be susceptible to "adversarial
attacks," in which small (or even imperceptible) changes to an image
completely alter it's class label according to a neural net.  This talk
explores several new angles on the concept of adversarial attacks.  First,
I explore the idea of "poisoning" attacks, which manipulate a network at
train time rather than test time.  Then, I address a fundamental question
about adversarial attacks:  Are adversarial attacks inevitable? I'll try to
answer this question from a both a theoretical and experimental perspective.

*Bio: *Tom Goldstein is an assistant professor at the University of
Maryland.  His research focuses on optimization methods for machine
learning and computer vision. Before joining the faculty at Maryland, Tom
completed his PhD in Mathematics at UCLA, and was a research scientist at
Rice University and Stanford University. He have been the recipient of
several awards, including SIAM’s DiPrima Prize, a DARPA Young Faculty
Award, and a Sloan Fellowship.


For more information on the machine learning seminar series (MLSS), please
request to join the group at https://groups.google.com/a/ttic.edu/d/forum/
mlss. If you are interested in presenting in the seminar, please send an
email to suriya at ttic.edu.


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Tue, Oct 23, 2018 at 10:49 AM Mary Marre <mmarre at ttic.edu> wrote:

> *When:         *Friday October 26, 11am-12pm
>
> *Where:        *Room 526, TTIC 6045 S Kenwood Avenue
>
> *Who:           *Thomas Goldstein, University of Maryland
>
> *Title:           *A New Take on Adversarial Examples
>
> *Abstract: *Neural networks perform extremely well at object recognition
> tasks, sometimes even meeting or exceeding human performance.  However,
> neural networks have recently been shown to be susceptible to "adversarial
> attacks," in which small (or even imperceptible) changes to an image
> completely alter it's class label according to a neural net.  This talk
> explores several new angles on the concept of adversarial attacks.  First,
> I explore the idea of "poisoning" attacks, which manipulate a network at
> train time rather than test time.  Then, I address a fundamental question
> about adversarial attacks:  Are adversarial attacks inevitable? I'll try to
> answer this question from a both a theoretical and experimental perspective.
>
> *Bio: *Tom Goldstein is an assistant professor at the University of
> Maryland.  His research focuses on optimization methods for machine
> learning and computer vision. Before joining the faculty at Maryland, Tom
> completed his PhD in Mathematics at UCLA, and was a research scientist at
> Rice University and Stanford University. He have been the recipient of
> several awards, including SIAM’s DiPrima Prize, a DARPA Young Faculty
> Award, and a Sloan Fellowship.
>
>
> For more information on the machine learning seminar series (MLSS), please
> request to join the group at https://groups.google.com/a/ttic.edu/d/forum/
> mlss. If you are interested in presenting in the seminar, please send an
> email to suriya at ttic.edu.
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20181026/1464ec21/attachment-0001.html>