29 citations · 129 across the 19 of their papers we have counts for
23 papers
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
Adda Akram Bendoukha, Heber Hwang Arcolezi, Nesrine Kaaniche +1
Federated Learning enables collaborative model training across decentralized data sources without data transfer. Averaging-based FL is limited by the presence of non-IID data, whic…
Beyond Epsilon: A Principled QIF Framework for Local Differential Privacy
Ramon G. Gonze, Natasha Fernandes, Heber H. Arcolezi +2
Local Differential Privacy (LDP) has become the de facto standard for privacy-preserving data collection in large-scale systems, in particular for the purpose of estimating frequen…
Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)
Patricia Guerra-Balboa, Annika Sauer, Héber H. Arcolezi +1
Differential Privacy (DP) is widely adopted in data management systems to enable data sharing with formal disclosure guarantees. A central systems challenge is understanding how DP…
Estimating the True Distribution of Data Collected with Randomized Response
Carlos Antonio Pinzón, Ehab ElSalamouny, Lucas Massot +3
Randomized Response (RR) is a protocol designed to collect and analyze categorical data with local differential privacy guarantees. It has been used as a building block of mechanis…
Private Frequency Estimation Via Residue Number Systems
Héber H. Arcolezi
We present \textsf{ModularSubsetSelection} (MSS), a new algorithm for locally differentially private (LDP) frequency estimation. Given a universe of size and users, our $\v…
How Tough Is Location Anonymization? Re-identifying 100K Real-User Trajectories in Japan
Abhishek Kumar Mishra, Mathieu Cunche, Heber H. Arcolezi
Mobility traces are among the most revealing forms of personal data, yet trajectory releases are often protected only by ad hoc transformations. We stress-test such practices on re…
Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairness
Héber H. Arcolezi, Mina Alishahi, Adda-Akram Bendoukha +1
Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers.…
Revisiting Locally Differentially Private Protocols: Towards Better Trade-offs in Privacy, Utility, and Attack Resistance
Héber H. Arcolezi, Sébastien Gambs
Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms th…
Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
Cédric Eichler, Nathan Champeil, Nicolas Anciaux +3
The rise of Large Language Models (LLMs) has triggered legal and ethical concerns, especially regarding the unauthorized use of copyrighted materials in their training datasets. Th…
A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
Karima Makhlouf, Tamara Stefanovic, Heber H. Arcolezi +1
Machine learning (ML) algorithms rely primarily on the availability of training data, and, depending on the domain, these data may include sensitive information about the data prov…
On the Impact of Multi-dimensional Local Differential Privacy on Fairness
Karima Makhlouf, Heber H. Arcolezi, Sami Zhioua +2
Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decision…
Causal Discovery Under Local Privacy
Rūta Binkytė, Carlos Pinzón, Szilvia Lestyán +3
Differential privacy is a widely adopted framework designed to safeguard the sensitive information of data providers within a data set. It is based on the application of controlled…
Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective
Héber H. Arcolezi, Sébastien Gambs
While the existing literature on Differential Privacy (DP) auditing predominantly focuses on the centralized model (e.g., in auditing the DP-SGD algorithm), we advocate for extendi…
On the Utility Gain of Iterative Bayesian Update for Locally Differentially Private Mechanisms
Héber H. Arcolezi, Selene Cerna, Catuscia Palamidessi
This paper investigates the utility gain of using Iterative Bayesian Update (IBU) for private discrete distribution estimation using data obfuscated with Locally Differentially Pri…
(Local) Differential Privacy has NO Disparate Impact on Fairness
Héber H. Arcolezi, Karima Makhlouf, Catuscia Palamidessi
In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb t…
Frequency Estimation of Evolving Data Under Local Differential Privacy
Héber H. Arcolezi, Carlos Pinzón, Catuscia Palamidessi +1
Collecting and analyzing evolving longitudinal data has become a common practice. One possible approach to protect the users' privacy in this context is to use local differential p…
On the Risks of Collecting Multidimensional Data Under Local Differential Privacy
Héber H. Arcolezi, Sébastien Gambs, Jean-François Couchot +1
The private collection of multiple statistics from a population is a fundamental statistical problem. One possible approach to realize this is to rely on the local model of differe…
Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
Héber H. Arcolezi, Jean-François Couchot, Denis Renaud +2
This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-o…
Multi-Freq-LDPy: Multiple Frequency Estimation Under Local Differential Privacy in Python
Héber H. Arcolezi, Jean-François Couchot, Sébastien Gambs +2
This paper introduces the multi-freq-ldpy Python package for multiple frequency estimation under Local Differential Privacy (LDP) guarantees. LDP is a gold standard for achieving l…
Production of Categorical Data Verifying Differential Privacy: Conception and Applications to Machine Learning
Héber H. Arcolezi
Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive,…
Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates
Héber H. Arcolezi, Jean-François Couchot, Bechara Al Bouna +1
This paper investigates the problem of collecting multidimensional data throughout time (i.e., longitudinal studies) for the fundamental task of frequency estimation under Local Di…
Random Sampling Plus Fake Data: Multidimensional Frequency Estimates With Local Differential Privacy
Héber H. Arcolezi, Jean-François Couchot, Bechara Al Bouna +1
With local differential privacy (LDP), users can privatize their data and thus guarantee privacy properties before transmitting it to the server (a.k.a. the aggregator). One primar…
RISE Controller Tuning and System Identification Through Machine Learning for Human Lower Limb Rehabilitation via Neuromuscular Electrical Stimulation
Héber H. Arcolezi, Willian R. B. M. Nunes, Rafael A. de Araujo +4
Neuromuscular electrical stimulation (NMES) has been effectively applied in many rehabilitation treatments of individuals with spinal cord injury (SCI). In this context, we introdu…