Search Results for author:
Found 8 papers, 3 papers with code
Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists
Differentially-private (DP) mechanisms can be embedded into the design of a machine learningalgorithm to protect the resulting model against privacy leakage, although this often comes with asignificant loss of accuracy.
Trained Random Forests Completely Reveal your Dataset
Even with bootstrap aggregation, the majority of the data can also be reconstructed.
SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning
Machine learning techniques are increasingly used for high-stakes decision-making, such as college admissions, loan attribution or recidivism prediction.
Probabilistic Dataset Reconstruction from Interpretable Models
In addition, we demonstrate that under realistic assumptions regarding the interpretable models' structure, the uncertainty of the reconstruction can be computed efficiently.
Learning Optimal Fair Scoring Systems for Multi-Class Classification
In this paper, we use Mixed-Integer Linear Programming (MILP) techniques to produce inherently interpretable scoring systems under sparsity and fairness constraints, for the general multi-class classification setup.
Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods
The advantages of such models over classical ones are two-fold: 1) They grant users precise control over the level of transparency of the system and 2) They can potentially perform better than a standalone black box since redirecting some of the inputs to an interpretable model implicitly acts as regularization.
Exploiting Fairness to Enhance Sensitive Attributes Reconstruction
More precisely, we propose a generic reconstruction correction method, which takes as input an initial guess made by the adversary and corrects it to comply with some user-defined constraints (such as the fairness information) while minimizing the changes in the adversary's guess.
Learning Fair Rule Lists
While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interpretable by design often display poor accuracy/fairness tradeoffs in comparison with their non-interpretable counterparts.
