Ulrich Aïvodji
Sujet de mémoire/thèse
Technologies respectueuses de la vie privée pour le covoiturage
Autre
I am a postdoctoral researcher at UQAM, working with Sébastien Gambs. My research interests are data privacy, optimization, and machine learning. My current research concerns privacy, interpretability, and fairness in machine learning.
I earned my Ph.D. in Computer Science at Université Toulouse III, under the supervision of Marie-José Huguet and Marc-Olivier Killijian. During my Ph.D. I was affiliated to LAAS-CNRS, a member of both ROC and TSF research groups, and have worked on privacy enhancing technologies for ridesharing.
"SoK: Taming the Triangle - On the Interplays between Fairness, Interpretability and Privacy in Machine Learning"2308.161912023
"Probabilistic Dataset Reconstruction from Interpretable Models"2nd IEEE Conference on Secure and Trustworthy Machine Learning2024
"Improving fairness generalization through a sample-robust optimization method"Machine Learning11262131-21922023
"Exploiting Fairness to Enhance Sensitive Attributes Reconstruction"2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)2023
Ali Shahin Shamsabadi, Mohammad Yaghini, Natalie Dullerud, Sierra Calanda WyllieUlrich AïvodjiAisha AlaagibSébastien Gambs et
Nicolas Papernot
"Washing The Unwashable : On The (Im)possibility of Fairwashing Detection"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS 20222022
"Leveraging Integer Linear Programming to Learn Optimal Fair Rule Lists"Integration of Constraint Programming, Artificial Intelligence, and Operations Research13292Lecture Notes in Computer ScienceSpringer103-1192022
"Local Data Debiasing for Fairness Based on Generative Adversarial Training" Algorithms 1438732021https://doi.org/10.3390/a14030087
"FairCORELS, an Open-Source Library for Learning Fair Rule Lists"CIKM '21: The 30th {ACM} International Conference on Information and Knowledge ManagementACM4665-4669102021
"Model extraction from counterfactual explanations"CoRR abs/2009.018842020https://arxiv.org/abs/2009.01884
"IOTFLA : A Secured and Privacy-Preserving Smart Home Architecture Implementing Federated Learning"IEEE Symposium on Security and Privacy Workshops175-1802019
"Fairwashing: the risk of rationalization"ICML161-1702019
"GAMIN: An Adversarial Approach to Black-Box Model Inversion"1906.118352019
"Agnostic data debiasing through a local sanitizer learnt from an adversarial network approach"1906.078582019
