Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Medina, Andrés Muñoz"'
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
Unsupervised pre-training is a common step in developing computer vision models and large language models. In this setting, the absence of labels requires the use of similarity-based loss functions, such as contrastive loss, that favor minimizing the
Externí odkaz:
http://arxiv.org/abs/2310.03104
New regulations and increased awareness of data privacy have led to the deployment of new and more efficient differentially private mechanisms across public institutions and industries. Ensuring the correctness of these mechanisms is therefore crucia
Externí odkaz:
http://arxiv.org/abs/2307.05608
Autor:
Bravo-Hermsdorff, Gecia, Busa-Fekete, Róbert, Ghavamzadeh, Mohammad, Medina, Andres Muñoz, Syed, Umar
Modern statistical estimation is often performed in a distributed setting where each sample belongs to a single user who shares their data with a central server. Users are typically concerned with preserving the privacy of their samples, and also wit
Externí odkaz:
http://arxiv.org/abs/2305.07751
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
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:
Epasto, Alessandro, Mao, Jieming, Medina, Andres Munoz, Mirrokni, Vahab, Vassilvitskii, Sergei, Zhong, Peilin
The streaming model of computation is a popular approach for working with large-scale data. In this setting, there is a stream of items and the goal is to compute the desired quantities (usually data statistics) while making a single pass through the
Externí odkaz:
http://arxiv.org/abs/2301.05605
When working with user data providing well-defined privacy guarantees is paramount. In this work, we aim to manipulate and share an entire sparse dataset with a third party privately. In fact, differential privacy has emerged as the gold standard of
Externí odkaz:
http://arxiv.org/abs/2207.06358
We present a differentially private algorithm for releasing the sequence of $k$ elements with the highest counts from a data domain of $d$ elements. The algorithm is a "joint" instance of the exponential mechanism, and its output space consists of al
Externí odkaz:
http://arxiv.org/abs/2201.12333
Autor:
Bravo-Hermsdorff, Gecia, Busa-Fekete, Robert, Gunderson, Lee M., Medina, Andrés Munõz, Syed, Umar
Data anonymization is an approach to privacy-preserving data release aimed at preventing participants reidentification, and it is an important alternative to differential privacy in applications that cannot tolerate noisy data. Existing algorithms fo
Externí odkaz:
http://arxiv.org/abs/2201.12306