1 code implementation • 7 Mar 2024 • Nico Manzonelli, Wanrong Zhang, Salil Vadhan
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data.
no code implementations • 18 Oct 2023 • Lukman Olagoke, Salil Vadhan, Seth Neel
In this paper we study whether given access to a trained GAN, as well as fresh samples from the underlying distribution, if it is possible for an attacker to efficiently identify if a given point is a member of the GAN's training data.
no code implementations • 10 Jul 2020 • Daniel Alabi, Audra McMillan, Jayshree Sarathy, Adam Smith, Salil Vadhan
Economics and social science research often require analyzing datasets of sensitive personal information at fine granularity, with models fit to small subsets of the data.
3 code implementations • 14 Sep 2016 • Marco Gaboardi, James Honaker, Gary King, Jack Murtagh, Kobbi Nissim, Jonathan Ullman, Salil Vadhan
We provide an overview of PSI ("a Private data Sharing Interface"), a system we are developing to enable researchers in the social sciences and other fields to share and explore privacy-sensitive datasets with the strong privacy protections of differential privacy.
Cryptography and Security Computers and Society Methodology
no code implementations • 19 Apr 2016 • Kobbi Nissim, Uri Stemmer, Salil Vadhan
We present a new algorithm for locating a small cluster of points with differential privacy [Dwork, McSherry, Nissim, and Smith, 2006].
1 code implementation • 7 Feb 2016 • Marco Gaboardi, Hyun woo Lim, Ryan Rogers, Salil Vadhan
We propose new tests for goodness of fit and independence testing that like the classical versions can be used to determine whether a given model should be rejected or not, and that additionally can ensure differential privacy.
Statistics Theory Cryptography and Security Statistics Theory
no code implementations • 28 Apr 2015 • Mark Bun, Kobbi Nissim, Uri Stemmer, Salil Vadhan
Our sample complexity upper and lower bounds also apply to the tasks of learning distributions with respect to Kolmogorov distance and of properly PAC learning thresholds with differential privacy.