Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Calmon, Flavio du Pin"'
Autor:
Kulynych, Bogdan, Gomez, Juan Felipe, Kaissis, Georgios, Calmon, Flavio du Pin, Troncoso, Carmela
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the added noise i
Externí odkaz:
http://arxiv.org/abs/2407.02191
Autor:
Watson-Daniels, Jamelle, Calmon, Flavio du Pin, D'Amour, Alexander, Long, Carol, Parkes, David C., Ustun, Berk
Machine learning models in modern mass-market applications are often updated over time. One of the foremost challenges faced is that, despite increasing overall performance, these updates may flip specific model predictions in unpredictable ways. In
Externí odkaz:
http://arxiv.org/abs/2402.07745
Autor:
Hsu, Hsiang, Calmon, Flavio du Pin
Predictive multiplicity occurs when classification models with statistically indistinguishable performances assign conflicting predictions to individual samples. When used for decision-making in applications of consequence (e.g., lending, education,
Externí odkaz:
http://arxiv.org/abs/2206.01295
In this paper, we consider the problem of responding to a count query (or any other integer-valued queries) evaluated on a dataset containing sensitive attributes. To protect the privacy of individuals in the dataset, a standard practice is to add co
Externí odkaz:
http://arxiv.org/abs/2007.09374
Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estim
Externí odkaz:
http://arxiv.org/abs/1910.08109
Prediction problems often admit competing models that perform almost equally well. This effect challenges key assumptions in machine learning when competing models assign conflicting predictions. In this paper, we define predictive multiplicity as th
Externí odkaz:
http://arxiv.org/abs/1909.06677
This paper considers fair probabilistic binary classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints that are
Externí odkaz:
http://arxiv.org/abs/1906.00066
We introduce a tunable measure for information leakage called maximal alpha-leakage. This measure quantifies the maximal gain of an adversary in inferring any (potentially random) function of a dataset from a release of the data. The inferential capa
Externí odkaz:
http://arxiv.org/abs/1809.09231
Autor:
Calmon, Flavio du Pin
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 143-150).
In this thesis, we study
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 143-150).
In this thesis, we study
Externí odkaz:
http://hdl.handle.net/1721.1/101567
Autor:
Calmon, Flavio du Pin, Médard, Muriel, Varia, Mayank, Duffy, Ken R., Christiansen, Mark M., Zeger, Linda M.
We present information-theoretic definitions and results for analyzing symmetric-key encryption schemes beyond the perfect secrecy regime, i.e. when perfect secrecy is not attained. We adopt two lines of analysis, one based on lossless source coding,
Externí odkaz:
http://arxiv.org/abs/1503.08513