Heber Hwang Arcolezi has a total of 66 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Data Poisoning in Longitudinal Local Differential Privacy: Attacks and Analysis

    by Antônio A. Marreiras Neto, Héber H. Arcolezi, Javam C. Machado

  • Open Access

    Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data

    by Maryam Babaei, Yingke Wang, Hadrien Lautraite, Héber H. Arcolezi, Ulrich Aïvodji, Sébastien Gambs


  • Production of categorical data verifying differential privacy : conception and applications to machine learning

    by HébEr Hwang Arcolezi

    Production de données catégorielles respectant la confidentialité différentielle : conception et applications au apprentissage automatique: Les organisations privées et publiques collectent et analysent régulièrement des données numérisées sur leurs associés, volontaires, clients, etc. Cependant, comme la plupart des données personnelles sont sensibles, la conception de systèmes préservant la vie privée pour se conformer aux lois sur la confidentialité des données, par exemple le règlement général sur la protection des données, constitue un défi majeur. La confidentialité différentielle (DP) est une définition formelle qui permet de quantifier le compromis entre confidentialité et utilité. Avec le modèle de DP local (LDP), les utilisateurs peuvent sanitizer leurs données localement avant de les transmettre au serveur.L'objectif de cette thèse est donc double : O1) Améliorer l'utilité et la confidentialité des protocoles LDP pour l'estimation de fréquence, qui est fondamentale pour l'apprentissage statistique. Et O2) Proposer des systèmes préservant la vie privée pour les tâches de data mining avec des garanties DP.Pour O1, nous avons d'abord abordé le problème sous deux angles multiples, à savoir de multiples attributs et de multiples collections dans le temps (études longitudinales), tout en nous concentrant sur l'utilité. Ensuite, nous avons concentré notre attention sur l'aspect des attributs multiples uniquement, dans lequel nous avons proposé une solution axée sur la confidentialité tout en préservant l'utilité. Dans les deux cas, nous démontrons par des validations analytiques et expérimentales les avantages de nos solutions proposées par rapport aux protocoles de l'état de l'art.Pour O2, nous avons proposé des systèmes basés sur l'apprentissage automatique (ML) pour résoudre des problèmes du monde réel tout en assurant des garanties de DP. En effet, nous avons principalement utilisé le paramètre de perturbation des données d'entrée de la littérature sur l'exploration de données préservant la confidentialité. Il s'agit de la situation dans laquelle l'ensemble des données est perturbé indépendamment et, dès lors, nous avons mis en œuvre des algorithmes LDP du point de vue du propriétaire centralisé des données. Dans tous les cas, nous avons conclu que les modèles ML différentiellement privés atteignent presque les mêmes performances que les modèles non privés.

  • Open Access

    Private Frequency Estimation Via Residue Number Systems

    by Héber H. Arcolezi

    We present \textsf{ModularSubsetSelection} (MSS), a new algorithm for locally differentially private (LDP) frequency estimation. Given a universe of size $k$ and $n$ users, our $\varepsilon$-LDP mechanism encodes each input via a Residue Number System (RNS) over $\ell$ pairwise-coprime moduli $m_0, \ldots, m_{\ell-1}$, and reports a randomly chosen index $j \in [\ell]$ along with the perturbed residue using the statistically optimal \textsf{SubsetSelection} (SS) (Wang et al. 2016). This design reduces the user communication cost from $Θ\bigl(ω\log_2(k/ω)\bigr)$ bits required by standard SS (with $ω\approx k/(e^\varepsilon+1)$) down to $\lceil \log_2 \ell \rceil + \lceil \log_2 m_j \rceil$ bits, where $m_j < k$. Server-side decoding runs in $Θ(n + r k \ell)$ time, where $r$ is the number of LSMR (Fong and Saunders 2011) iterations. In practice, with well-conditioned moduli (\textit{i.e.}, constant $r$ and $\ell = Θ(\log k)$), this becomes $Θ(n + k \log k)$. We prove that MSS achieves worst-case MSE within a constant factor of state-of-the-art protocols such as SS and \textsf{ProjectiveGeometryResponse} (PGR) (Feldman et al. 2022) while avoiding the algebraic prerequisites and dynamic-programming decoder required by PGR. Empirically, MSS matches the estimation accuracy of SS, PGR, and \textsf{RAPPOR} (Erlingsson, Pihur, and Korolova 2014) across realistic $(k, \varepsilon)$ settings, while offering faster decoding than PGR and shorter user messages than SS. Lastly, by sampling from multiple moduli and reporting only a single perturbed residue, MSS achieves the lowest reconstruction-attack success rate among all evaluated LDP protocols.

  • Open Access

    FADE: Federated Aggregation with Discrimination Elimination

    by Adda-Akram Bendoukha, Héber Hwang Arcolezi, Nesrine Kaaniche, Aymen Boudguiga, Renaud Sirdey, Pierre-Emmanuel Clet

  • Group fairness under obfuscated sensitive information

    by Héber Hwang Arcolezi, Karima Makhlouf, Catuscia Palamidessi

    In the era of Big Data, the development of artificial intelligence (AI) systems presents both opportunities and challenges, particularly concerning privacy and fairness. While differential privacy (DP) has emerged as a robust methodology for preserving privacy in real-world applications, its local variant (LDP) specifically addresses trust issues by removing the reliance on a centralized server. Equally critical, conducting fairness audits of AI systems helps identify and mitigate discriminatory outcomes in machine learning. Although the relationship between DP and fairness is inherently multifaceted, this paper offers a detailed empirical examination of how collecting multi-dimensional sensitive attributes under LDP affects fairness in binary classification tasks. Our findings reveal that LDP can slightly improve fairness without substantially degrading model performance—challenging the notion that DP necessarily exacerbates unfairness. We demonstrate these results by evaluating seven state-of-the-art LDP protocols on three benchmark datasets, using established group fairness metrics. Moreover, we propose a novel privacy budget allocation scheme that incorporates varying domain sizes of sensitive attributes, achieving a superior privacy–utility–fairness trade-off compared to existing solutions.


  • Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction

    by Cédric Eichler, Nathan Champeil, Nicolas Anciaux, Alexandra Bensamoun, Héber H. Arcolezi, José Maria De Fuentes


  • Open Access

    Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective

    by 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 extending this approach to audit Local DP (LDP). To achieve this, we introduce the LDP-Auditor framework for empirically estimating the privacy loss of locally differentially private mechanisms. This approach leverages recent advances in designing privacy attacks against LDP frequency estimation protocols. More precisely, through the analysis of numerous state-of-the-art LDP protocols, we extensively explore the factors influencing the privacy audit, such as the impact of different encoding and perturbation functions. Additionally, we investigate the influence of the domain size and the theoretical privacy loss parameters ϵ and δ on local privacy estimation. In-depth case studies are also conducted to explore specific aspects of LDP auditing, including distinguishability attacks on LDP protocols for longitudinal studies and multidimensional data. Finally, we present a notable achievement of our LDP-Auditor framework, which is the discovery of a bug in a state-of-the-art LDP Python package. Overall, our LDP-Auditor framework as well as our study offer valuable insights into the sources of randomness and information loss in LDP protocols. These contributions collectively provide a realistic understanding of the local privacy loss, which can help practitioners in selecting the LDP mechanism and privacy parameters that best align with their specific requirements. We open-sourced LDP-Auditor in [4].