[Theory] NOW: 7/17 Talks at TTIC: Jonathan Ullman, Northeastern University

Mary Marre mmarre at ttic.edu
Mon Jul 17 10:59:27 CDT 2023


*When:*        Monday, July 17, 2023 at* 11:00** a**m CT   *


*Where:       *Talk will be given *live, in-person* at

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 530


*Virtually:*  *via *Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=b4127f1c-18ab-4a94-bd01-b03b016ac212>*
)

                  *   ***Access limited to TTIC/UChicago (see info below)*


*Who: *         Jonathan Ullman, Northeastern University


------------------------------

*Title:*          Auditing Differentially Private Machine Learning


*Abstract: *A differentially private algorithm comes with a rigorous proof
that the algorithm satisfies a strong qualitative and quantitative privacy
guarantee, but these stylized mathematical guarantees can both overestimate
and underestimate the privacy afforded by the algorithm in a real
deployment.  In this talk I will motivate and describe my ongoing body of
work on using empirical auditing of differentially private machine learning
algorithms as a complement to the theory of differential privacy.  The talk
will discuss how auditing builds on the rich theory and practice of
membership-inference attacks, our work on auditing differentially private
stochastic gradient descent, and directions for future work.

*Bio: *Jonathan Ullman is an Associate Professor in the Khoury College of
Computer Sciences at Northeastern University.  Before joining Northeastern,
he received his PhD from Harvard in 2013, and in 2014 was a Junior Fellow
in the Simons Society of Fellows.   His research centers on privacy for
machine learning and statistics, and its surprising connections to topics
like statistical validity, robustness, cryptography, and fairness.  He has
been recognized with an NSF CAREER award and the Ruth and Joel Spira
Outstanding Teacher Award.

*Host: *Avrim Blum <avrim at ttic.edu>

*Access to this livestream is limited to *TTIC / UChicago* (press panopto
link and login to your UChicago account).



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL  60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Mon, Jul 17, 2023 at 10:11 AM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*        Monday, July 17, 2023 at* 11:00** a**m CT   *
>
>
> *Where:       *Talk will be given *live, in-person* at
>
>                    TTIC, 6045 S. Kenwood Avenue
>
>                    5th Floor, Room 530
>
>
> *Virtually:*  *via *Panopto (*livestream
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=b4127f1c-18ab-4a94-bd01-b03b016ac212>*
> )
>
>                   *   ***Access limited to TTIC/UChicago (see info below)*
>
>
> *Who: *         Jonathan Ullman, Northeastern University
>
>
> ------------------------------
>
> *Title:*          Auditing Differentially Private Machine Learning
>
>
> *Abstract: *A differentially private algorithm comes with a rigorous
> proof that the algorithm satisfies a strong qualitative and quantitative
> privacy guarantee, but these stylized mathematical guarantees can both
> overestimate and underestimate the privacy afforded by the algorithm in a
> real deployment.  In this talk I will motivate and describe my ongoing body
> of work on using empirical auditing of differentially private machine
> learning algorithms as a complement to the theory of differential privacy.
> The talk will discuss how auditing builds on the rich theory and practice
> of membership-inference attacks, our work on auditing differentially
> private stochastic gradient descent, and directions for future work.
>
> *Bio: *Jonathan Ullman is an Associate Professor in the Khoury College of
> Computer Sciences at Northeastern University.  Before joining Northeastern,
> he received his PhD from Harvard in 2013, and in 2014 was a Junior Fellow
> in the Simons Society of Fellows.   His research centers on privacy for
> machine learning and statistics, and its surprising connections to topics
> like statistical validity, robustness, cryptography, and fairness.  He has
> been recognized with an NSF CAREER award and the Ruth and Joel Spira
> Outstanding Teacher Award.
>
> *Host: *Avrim Blum <avrim at ttic.edu>
>
> *Access to this livestream is limited to *TTIC / UChicago* (press panopto
> link and login to your UChicago account).
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue, Rm 517*
> *Chicago, IL  60637*
> *773-834-1757*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Mon, Jul 10, 2023 at 5:20 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:*        Monday, July 17, 2023 at* 11:00** a**m CT   *
>>
>>
>> *Where:       *Talk will be given *live, in-person* at
>>
>>                    TTIC, 6045 S. Kenwood Avenue
>>
>>                    5th Floor, Room 530
>>
>>
>> *Virtually:*  *via *Panopto (*livestream
>> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=b4127f1c-18ab-4a94-bd01-b03b016ac212>*
>> )
>>
>>                   *   ***Access limited to TTIC/UChicago (see info
>> below)*
>>
>>
>> *Who: *         Jonathan Ullman, Northeastern University
>>
>>
>> ------------------------------
>>
>> *Title:*          Auditing Differentially Private Machine Learning
>>
>>
>> *Abstract: *A differentially private algorithm comes with a rigorous
>> proof that the algorithm satisfies a strong qualitative and quantitative
>> privacy guarantee, but these stylized mathematical guarantees can both
>> overestimate and underestimate the privacy afforded by the algorithm in a
>> real deployment.  In this talk I will motivate and describe my ongoing body
>> of work on using empirical auditing of differentially private machine
>> learning algorithms as a complement to the theory of differential privacy.
>> The talk will discuss how auditing builds on the rich theory and practice
>> of membership-inference attacks, our work on auditing differentially
>> private stochastic gradient descent, and directions for future work.
>>
>> *Bio: *Jonathan Ullman is an Associate Professor in the Khoury College
>> of Computer Sciences at Northeastern University.  Before joining
>> Northeastern, he received his PhD from Harvard in 2013, and in 2014 was a
>> Junior Fellow in the Simons Society of Fellows.   His research centers on
>> privacy for machine learning and statistics, and its surprising connections
>> to topics like statistical validity, robustness, cryptography, and
>> fairness.  He has been recognized with an NSF CAREER award and the Ruth and
>> Joel Spira Outstanding Teacher Award.
>>
>> *Host: *Avrim Blum <avrim at ttic.edu>
>>
>> *Access to this livestream is limited to *TTIC / UChicago* (press
>> panopto link and login to your UChicago account).
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue, Rm 517*
>> *Chicago, IL  60637*
>> *773-834-1757*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20230717/e6ba0648/attachment-0001.html>


More information about the Theory mailing list