Search Results for author:
Found 15 papers, 5 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.
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
We introduce a privacy auditing scheme for ML models that relies on membership inference attacks using generated data as "non-members".
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.
Crypto'Graph: Leveraging Privacy-Preserving Distributed Link Prediction for Robust Graph Learning
The use of Crypto'Graph is illustrated for defense against graph poisoning attacks, in which it is possible to identify potential adversarial links without compromising the privacy of the graphs of individual parties.
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.
Membership Inference Attack for Beluga Whales Discrimination
To efficiently monitor the growth and evolution of a particular wildlife population, one of the main fundamental challenges to address in animal ecology is the re-identification of individuals that have been previously encountered but also the discrimination between known and unknown individuals (the so-called "open-set problem"), which is the first step to realize before re-identification.
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.
Fair mapping
In addition, our approach can be specialized to model existing state-of-the-art approaches, thus proposing a unifying view on these methods.
Characterizing the risk of fairwashing
In particular, we show that fairwashed explanation models can generalize beyond the suing group (i. e., data points that are being explained), meaning that a fairwashed explainer can be used to rationalize subsequent unfair decisions of a black-box model.
Model extraction from counterfactual explanations
Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes.
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks
However, nothing prevents the service provider to infer private and sensitive information about a user such as health or demographic attributes. In this paper, we present DySan, a privacy-preserving framework to sanitize motion sensor data against unwanted sensitive inferences (i. e., improving privacy) while limiting the loss of accuracy on the physical activity monitoring (i. e., maintaining data utility).
GAMIN: An Adversarial Approach to Black-Box Model Inversion
While some model inversion attacks have been developed in the past in the black-box attack setting, in which the adversary does not have direct access to the structure of the model, few of these have been conducted so far against complex models such as deep neural networks.
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.
Adversarial training approach for local data debiasing
The widespread use of automated decision processes in many areas of our society raises serious ethical issues concerning the fairness of the process and the possible resulting discriminations.
Fairwashing: the risk of rationalization
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes.
