Assistant Professor · ÉTS Montréal

Héber H. Arcolezi

I design, analyze, and audit privacy-preserving machine learning systems, with a focus on differential privacy, inference risks, and fairness.

Differential PrivacyPrivacy AuditingFairness in MLPrivacy–Utility Trade-offs

About

I am an Assistant Professor in the Department of Software and Information Technology Engineering at ÉTS Montréal, where I co-lead the Trustworthy Information Systems Lab (TISL) research group. Previously, I was a Tenured Research Scientist at Inria Grenoble.

Background

I received my Ph.D. in Computer Science from the University of Bourgogne Franche-Comté (UBFC), my M.Sc. in Electrical Engineering from the São Paulo State University (UNESP), and my B.Eng. in Electrical Engineering from the Mato Grosso State University (UNEMAT).

Research Focus

My research addresses the technical challenges of Responsible AI through the lenses of fairness, privacy-preserving techniques, and explainability. My goal is to design systems that are both mathematically private and socially equitable.

Privacy-preserving machine learningDifferential privacy, private learning, and private representations.
Privacy auditingInference attacks, leakage assessment, and empirical audits.
Fairness & equityPrivacy–fairness trade-offs and differentially private fair learning.
Real-world applicationsHealth, mobility, and other sensitive-data domains.
Explore research projects →

Recent News

Jun 2026
📄 Our paper "Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data" has been accepted at PETS 2026 and can be accessed at https://arxiv.org/abs/2607.07471!
Apr 2026
🔍 I’ll be serving in the PC of the 27th Privacy Enhancing Technologies Symposium (PETS 2027).
Mar 2026
🔍 I’ll be serving in the PC of the 53rd International Conference on Very Large Data Bases (VLDB 2027).
Show all news (12 more)
Feb 2026
📄 Our paper "Revisiting Locally Differentially Private Protocols: Towards Better Trade-offs in Privacy, Utility, and Attack Resistance" has been accepted at ICDE 2026 and can be accessed at https://arxiv.org/abs/2503.01482!
Feb 2026
📄 Our paper "Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing" has been accepted at VLDB 2026 and can be accessed at https://arxiv.org/abs/2603.12142!
Feb 2026
🎉 I have officially joined ÉTS Montréal as an Assistant Professor!
Nov 2025
🔍 I’ll be serving in the (Privacy and Anonymity Track) PC of the *ACM Conference on Computer and Communications Security* (CCS 2026).
Aug 2025
🔍I’ll be serving in the PC of the *40th Annual AAAI Conference on Artificial Intelligence* (AAAI 2026).
Jul 2025
📄 Our paper "Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairness" has been accepted at ECAI 2025 and can be accessed at https://arxiv.org/abs/2505.07985.

Contact

I am always happy to discuss the possibility of new collaborations.

Postal Address
1100, rue Notre-Dame Ouest, Montréal (Qc) H3C 1K3, Canada.

Last update: Oct 7, 2026.