Search Results for author:
Found 23 papers, 10 papers with code
Causal Discovery Under Local Privacy
It is based on the application of controlled noise at the interface between the server that stores and processes the data, and the data consumers.
Online Sensitivity Optimization in Differentially Private Learning
Training differentially private machine learning models requires constraining an individual's contribution to the optimization process.
Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
FL was proposed as a stepping-stone towards privacy-preserving machine learning, but it has been shown vulnerable to issues such as leakage of private information, lack of personalization of the model, and the possibility of having a trained model that is fairer to some groups than to others.
On the Utility Gain of Iterative Bayesian Update for Locally Differentially Private Mechanisms
This paper investigates the utility gain of using Iterative Bayesian Update (IBU) for private discrete distribution estimation using data obfuscated with Locally Differentially Private (LDP) mechanisms.
BaBE: Enhancing Fairness via Estimation of Latent Explaining Variables
We consider the problem of unfair discrimination between two groups and propose a pre-processing method to achieve fairness.
Survey on Fairness Notions and Related Tensions
Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy.
Causal Discovery for Fairness
Existing causal approaches to fairness in the literature do not address this problem and assume that the causal model is available.
Group privacy for personalized federated learning
To cope with the issue of protecting the privacy of the clients and allowing for personalized model training to enhance the fairness and utility of the system, we propose a method to provide group privacy guarantees exploiting some key properties of $d$-privacy which enables personalized models under the framework of FL.
Leveraging Adversarial Examples to Quantify Membership Information Leakage
The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today.
Identifiability of Causal-based Fairness Notions: A State of the Art
This paper is a compilation of the major identifiability results which are of particular relevance for machine learning fairness.
On the impossibility of non-trivial accuracy under fairness constraints
One of the main concerns about fairness in machine learning (ML) is that, in order to achieve it, one may have to trade off some accuracy.
DOCTOR: A Simple Method for Detecting Misclassification Errors
Deep neural networks (DNNs) have shown to perform very well on large scale object recognition problems and lead to widespread use for real-world applications, including situations where DNN are implemented as "black boxes".
Bounding Information Leakage in Machine Learning
We present a novel formalism, generalizing membership and attribute inference attack setups previously studied in the literature and connecting them to memorization and generalization.
Information Leakage Games: Exploring Information as a Utility Function
A common goal in the areas of secure information flow and privacy is to build effective defenses against unwanted leakage of information.
Survey on Causal-based Machine Learning Fairness Notions
Addressing the problem of fairness is crucial to safely use machine learning algorithms to support decisions with a critical impact on people's lives such as job hiring, child maltreatment, disease diagnosis, loan granting, etc.
Machine learning fairness notions: Bridging the gap with real-world applications
Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities.
Estimating g-Leakage via Machine Learning
A feature of our approach is that it does not require to estimate the conditional probabilities, and that it is suitable for a large class of ML algorithms.
Feature selection in machine learning: Rényi min-entropy vs Shannon entropy
Many algorithms for feature selection in the literature have adopted the Shannon-entropy-based mutual information.
Optimal Obfuscation Mechanisms via Machine Learning
The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the classifier, that tries to de-obfuscate the data.
F-BLEAU: Fast Black-box Leakage Estimation
The state-of-the-art method for estimating these leakage measures is the frequentist paradigm, which approximates the system's internals by looking at the frequencies of its inputs and outputs.
Cryptography and Security
Geo-Indistinguishability: Differential Privacy for Location-Based Systems
The growing popularity of location-based systems, allowing unknown/untrusted servers to easily collect huge amounts of information regarding users' location, has recently started raising serious privacy concerns.
Cryptography and Security C.2.0; K.4.1
