Héber H. Arcolezi

Héber H. Arcolezi

Research Scientist @ Inria Grenoble - Rhône-Alpes Research focus: Differential Privacy & Ethics of AI.

About Me

Welcome! I’m a tenured research scientist at Inria Grenoble working with the Privatics team. Previously, I was a postdoctoral researcher in the Comète team at Inria Saclay. I received my Ph.D. in Computer Science from the University Bourgogne Franche-Comté (UBFC) and my M.Sc. in Electrical Engineering from the São Paulo State University (UNESP).

Currently, my research interests are differential privacy and ethical aspects of machine learning (e.g., privacy and fairness issues).

Recent News

  • [Feb-25] I’ll give a Keynote talk on “Intersections of Fairness and Privacy: A Local Differential Privacy Perspective” at the (9th GDR RSD/ASF Winter School on Distributed Systems \& Networks 2025).
  • [Oct-24] My project “AI-PULSE: Aligning Privacy, UtiLity, and FairnesS for ResponsiblE AI”, accepted for funding by the ANR AAPG (JCJC - Young researchers) call, is officially started.
  • [Sep-24] Our paper “Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction” has been accepted at WISE 2024 and can be accessed at https://arxiv.org/abs/2408.05968.
  • [Aug-24] I’ll give a tutorial on “Securing Data with Local Differential Privacy: Concepts, Protocols, and Practical Applications” at the SAC Summer School (SAC 2024).
  • [Aug-24] I’ll be serving in the PC of the 13th International Conference on Learning Representations (ICLR 2025).
  • [Aug-24] I’ll be serving in the PC of the 34th USENIX Security Symposium (USENIX Security 2025).
  • [May-24] Our paper “Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective” has been accepted at PETS 2024 and can be accessed at https://arxiv.org/abs/2309.01597.
  • [Apr-24] Our paper “A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results” has been accepted at CSF 2024 and can be accessed at https://arxiv.org/abs/2405.14725.
  • [Apr-24] Our paper “On the impact of multi-dimensional local differential privacy on fairness” has been accepted at ECML PKDD 2024 (Journal Track) and can be accessed at https://arxiv.org/abs/2312.04404.
  • [Feb-24] I’ll be serving in the PC of the 25th Privacy Enhancing Technologies Symposium (PETS 2025).
  • [Feb-24] Our associated team AUDIT-PAIR proposal with the UQAM has been approved and launched, focusing on advancing AI system auditing for privacy and fairness.
  • [Jan-24] Our paper “Causal Discovery Under Local Privacy” has been accepted at CLeaR 2024 and can be accessed at https://arxiv.org/abs/2311.04037.
  • [Jan-24] I’ll be serving in the PC of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024).
  • [Jan-24] I’ll be serving in the PC of the 7th ACM Conference on Fairness, Accountability, and Transparency (FAccT 2024).
  • [Jan-24] I’ll be serving in the PC of the 31st Selected Areas in Cryptography Conference (SAC 2024).
  • [Dec-24] My project “Exploring the Interplay of Differential Privacy and Fairness in ML” has been accepted for funding by the MIAI Open Call.
  • [Dec-23] I’ll be serving in the (Privacy and Anonymity Track) PC of the 31st ACM Conference on Computer and Communications Security (CCS 2024).

Contact

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

  • Email: heber.hwang-arcolezi@inria.fr
  • Postal Address: 655 Av. de l’Europe, 38330 Montbonnot-Saint-Martin, France.

Last update: February 21st, 2025.