[Theory] NOW: [Talks at TTIC] 10/2 TTIC Colloquium: Boaz Barak, Harvard University

[Brandie Jones]

*When:*        Monday, October 2nd at *11:30am 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=fa5fb979-3d4c-4918-9abe-b08200ee655f>
)


*Who: *         Boaz Barak, Havard University

*Title:*   On Provable Copyright Protection for Generative Model
*Abstract:  *There is a growing concern that learned conditional generative
models may output samples that are substantially similar to some
copyrighted data C that was in their training set. We give a formal
definition of near access-freeness (NAF) and prove bounds on the
probability that a model satisfying this definition outputs a sample
similar to C, even if C is included in its training set.

Roughly speaking, a generative model p is k-NAF if for every potentially
copyrighted data C, the output of p diverges by at most k-bits from the
output of a model q that did not access C at all. We also give generative
model learning algorithms, which efficiently modify the original generative
model learning algorithm in a black box manner, that output generative
models with strong bounds on the probability of sampling protected content.
Furthermore, we provide promising experiments for both language
(transformers) and image (diffusion) generative models, showing minimal
degradation in output quality while ensuring strong protections against
sampling protected content.

Joint work with Nikhil Vyas and Sham Kakade. Paper appeared in ICML 2023
and is on https://arxiv.org/abs/2302.10870

*Host: Nati Srebro <nati at ttic.edu>*

-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
Working Remotely on Tuesdays
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20231002/fc23498e/attachment.html>