research
∙
09/01/2023
Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
Federated learning (FL) is a framework for training machine learning mod...
share
research
∙
07/15/2023
On the Utility Gain of Iterative Bayesian Update for Locally Differentially Private Mechanisms
This paper investigates the utility gain of using Iterative Bayesian Upd...
research
∙
07/06/2023
BaBE: Enhancing Fairness via Estimation of Latent Explaining Variables
We consider the problem of unfair discrimination between two groups and ...
research
∙
05/22/2023
Analyzing the Shuffle Model through the Lens of Quantitative Information Flow
Local differential privacy (LDP) is a variant of differential privacy (D...
research
∙
04/25/2023
(Local) Differential Privacy has NO Disparate Impact on Fairness
In recent years, Local Differential Privacy (LDP), a robust privacy-pres...
research
∙
10/01/2022
Frequency Estimation of Evolving Data Under Local Differential Privacy
Collecting and analyzing evolving longitudinal data has become a common ...
research
∙
09/16/2022
Survey on Fairness Notions and Related Tensions
Automated decision systems are increasingly used to take consequential d...
research
∙
09/09/2022
Minimizing Information Leakage under Padding Constraints
An attacker can gain information of a user by analyzing its network traf...
research
∙
09/04/2022
On the Risks of Collecting Multidimensional Data Under Local Differential Privacy
The private collection of multiple statistics from a population is a fun...
research
∙
08/30/2022
On the (Im)Possibility of Estimating Various Notions of Differential Privacy
We analyze to what extent final users can infer information about the le...
research
∙
08/24/2022
Reconstruction of the distribution of sensitive data under free-will privacy
The local privacy mechanisms, such as k-RR, RAPPOR, and the geo-indistin...
research
∙
06/21/2022
Three-way optimization of privacy and utility of location data
With the recent bloom of data and the drive towards an information-based...
research
∙
06/14/2022
Causal Discovery for Fairness
It is crucial to consider the social and ethical consequences of AI and ...
research
∙
06/07/2022
Group privacy for personalized federated learning
Federated learning is a type of collaborative machine learning, where pa...
research
∙
06/04/2022
A privacy preserving querying mechanism with high utility for electric vehicles
With the recent rise in awareness about advancing towards a sustainable ...
research
∙
05/18/2022
Tight Differential Privacy Guarantees for the Shuffle Model with k-Randomized Response
Most differentially private (DP) algorithms assume a central model in wh...
research
∙
05/09/2022
Tight Differential Privacy Blanket for Shuffle Model
With the recent bloom of focus on digital economy, the importance of per...
research
∙
05/05/2022
Multi-Freq-LDPy: Multiple Frequency Estimation Under Local Differential Privacy in Python
This paper introduces the Python package for multiple frequency estimat...
research
∙
05/03/2022
Universal Optimality and Robust Utility Bounds for Metric Differential Privacy
We study the privacy-utility trade-off in the context of metric differen...
research
∙
03/17/2022
Leveraging Adversarial Examples to Quantify Membership Information Leakage
The use of personal data for training machine learning systems comes wit...
research
∙
03/11/2022
Identifiability of Causal-based Fairness Notions: A State of the Art
Machine learning algorithms can produce biased outcome/prediction, typic...
research
∙
11/30/2021
Establishing the Price of Privacy in Federated Data Trading
Personal data is becoming one of the most essential resources in today's...
research
∙
07/14/2021
On the impossibility of non-trivial accuracy under fairness constraints
One of the main concerns about fairness in machine learning (ML) is that...
research
∙
06/27/2021
An Incentive Mechanism for Trading Personal Data in Data Markets
With the proliferation of the digital data economy, digital data is cons...
research
∙
06/04/2021
DOCTOR: A Simple Method for Detecting Misclassification Errors
Deep neural networks (DNNs) have shown to perform very well on large sca...
research
∙
05/09/2021
Bounding Information Leakage in Machine Learning
Machine Learning services are being deployed in a large range of applica...
research
∙
12/22/2020
Information Leakage Games: Exploring Information as a Utility Function
A common goal in the areas of secure information flow and privacy is to ...
research
∙
11/06/2020
The Bayes Security Measure
Security system designers favor worst-case security measures, such as th...
research
∙
10/19/2020
Survey on Causal-based Machine Learning Fairness Notions
Addressing the problem of fairness is crucial to safely use machine lear...
research
∙
06/30/2020
On the Applicability of ML Fairness Notions
ML-based predictive systems are increasingly used to support decisions w...
research
∙
05/09/2020
Estimating g-Leakage via Machine Learning
This paper considers the problem of estimating the information leakage o...
research
∙
01/27/2020
Feature selection in machine learning: Rényi min-entropy vs Shannon entropy
Feature selection, in the context of machine learning, is the process of...
research
∙
09/06/2019
Full Convergence of the Iterative Bayesian Update and Applications to Mechanisms for Privacy Protection
The iterative Bayesian update (IBU) and the matrix inversion (INV) are t...
research
∙
06/28/2019
Utility-Preserving Privacy Mechanisms for Counting Queries
Differential privacy (DP) and local differential privacy (LPD) are frame...
research
∙
04/01/2019
Generating Optimal Privacy-Protection Mechanisms via Machine Learning
We consider the problem of obfuscating sensitive information while prese...
research
∙
02/04/2019
F-BLEAU: Fast Black-box Leakage Estimation
We consider the problem of measuring how much a system reveals about its...
research
∙
05/03/2018
Metric-based local differential privacy for statistical applications
Local differential privacy (LPD) is a distributed variant of differentia...
research
∙
03/27/2018
A Game-Theoretic Approach to Information-Flow Control via Protocol Composition
In the inference attacks studied in Quantitative Information Flow (QIF),...
research
∙
02/27/2018