Zobrazeno 1 - 10
of 112
pro vyhledávání: '"Dick, Travis"'
Autor:
Busa-Fekete, Róbert István, Dick, Travis, Gentile, Claudio, Medina, Andrés Muñoz, Smith, Adam, Swanberg, Marika
We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer the true label of an unlabeled example when provided with a private ver
Externí odkaz:
http://arxiv.org/abs/2406.02797
Autor:
Balcan, Maria-Florina1 ninamf@cs.cmu.edu, Dick, Travis2 tdick@google.com, Sandholm, Tuomas3 sandholm@cs.cmu.edu, Vitercik, Ellen4 vitercik@stanford.edu
Publikováno v:
Journal of the ACM. Apr2024, Vol. 71 Issue 2, p1-73. 73p.
Existing work on differentially private linear regression typically assumes that end users can precisely set data bounds or algorithmic hyperparameters. End users often struggle to meet these requirements without directly examining the data (and viol
Externí odkaz:
http://arxiv.org/abs/2306.00920
Autor:
Carey, CJ, Dick, Travis, Epasto, Alessandro, Javanmard, Adel, Karlin, Josh, Kumar, Shankar, Medina, Andres Munoz, Mirrokni, Vahab, Nunes, Gabriel Henrique, Vassilvitskii, Sergei, Zhong, Peilin
Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification risk in such user representations. Our framework, based on hypothesis t
Externí odkaz:
http://arxiv.org/abs/2304.07210
We propose a new definition of instance optimality for differentially private estimation algorithms. Our definition requires an optimal algorithm to compete, simultaneously for every dataset $D$, with the best private benchmark algorithm that (a) kno
Externí odkaz:
http://arxiv.org/abs/2303.01262
Autor:
Busa-Fekete, Robert Istvan, Choi, Heejin, Dick, Travis, Gentile, Claudio, medina, Andres Munoz
We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class labels at each bag is available. Albeit, the objective of the learner
Externí odkaz:
http://arxiv.org/abs/2302.03115
Autor:
Dick, Travis, Dwork, Cynthia, Kearns, Michael, Liu, Terrance, Roth, Aaron, Vietri, Giuseppe, Wu, Zhiwei Steven
A reconstruction attack on a private dataset $D$ takes as input some publicly accessible information about the dataset and produces a list of candidate elements of $D$. We introduce a new class of data reconstruction attacks based on randomized metho
Externí odkaz:
http://arxiv.org/abs/2211.03128
When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms with pred
Externí odkaz:
http://arxiv.org/abs/2210.11222
This paper introduces the first provably accurate algorithms for differentially private, top-down decision tree learning in the distributed setting (Balcan et al., 2012). We propose DP-TopDown, a general privacy preserving decision tree learning algo
Externí odkaz:
http://arxiv.org/abs/2012.10602
Autor:
Diana, Emily, Dick, Travis, Elzayn, Hadi, Kearns, Michael, Roth, Aaron, Schutzman, Zachary, Sharifi-Malvajerdi, Saeed, Ziani, Juba
We consider a variation on the classical finance problem of optimal portfolio design. In our setting, a large population of consumers is drawn from some distribution over risk tolerances, and each consumer must be assigned to a portfolio of lower ris
Externí odkaz:
http://arxiv.org/abs/2006.07281