Flávio P. Calmon
5 papers in the PaperMetrix corpus
Papers by this author
-
A Tunable Measure for Information Leakage
2018 · arXiv (Cornell University)
A tunable measure for information leakage called \textit{maximal $α$-leakage} is introduced. This measure quantifies the maximal gain of an adversary in refining a tilted version of its prior belief of any (potentially random) function of …
-
To Split or Not to Split: The Impact of Disparate Treatment in Classification
2020 · arXiv (Cornell University)
Disparate treatment occurs when a machine learning model yields different decisions for individuals based on a sensitive attribute (e.g., age, sex). In domains where prediction accuracy is paramount, it could potentially be acceptable to fit …
-
To Split or not to Split: The Impact of Disparate Treatment in Classification
2021 · IEEE Transactions on Information Theory
Disparate treatment occurs when a machine learning model produces different decisions for individuals based on a legally protected or sensitive attribute (e.g., age, sex). In domains where prediction accuracy is paramount, it could potentially be …
-
Arbitrary Decisions are a Hidden Cost of Differentially Private Training
2023
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data (e.g., adding Gaussian noise to clipped …
-
Optimizing Noise Distributions for Differential Privacy
2025 · arXiv (Cornell University)
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP, under a cost constraint. Rényi DP has the advantage …