55 citations · 151 across the 9 of their papers we have counts for
10 papers
Fairness Under Demographic Scarce Regime
Patrik Joslin Kenfack, Samira Ebrahimi Kahou, Ulrich Aïvodji
Most existing works on fairness assume the model has full access to demographic information. However, there exist scenarios where demographic information is partially available bec…
Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods
Julien Ferry, Gabriel Laberge, Ulrich Aïvodji
A hybrid model involves the cooperation of an interpretable model and a complex black box. At inference, any input of the hybrid model is assigned to either its interpretable or co…
Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations
Jessica Dai, Sohini Upadhyay, Ulrich Aivodji +2
As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting…
Characterizing the risk of fairwashing
Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs +1
Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capabi…
Model extraction from counterfactual explanations
Ulrich Aïvodji, Alexandre Bolot, Sébastien Gambs
Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes. Among post-hoc explanation t…
GAMIN: An Adversarial Approach to Black-Box Model Inversion
Ulrich Aïvodji, Sébastien Gambs, Timon Ther
Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their traini…
Learning Fair Rule Lists
Ulrich Aïvodji, Julien Ferry, Sébastien Gambs +2
As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that inte…
Adversarial training approach for local data debiasing
Ulrich Aïvodji, François Bidet, Sébastien Gambs +2
The widespread use of automated decision processes in many areas of our society raises serious ethical issues concerning the fairness of the process and the possible resulting disc…
Privacy in trajectory micro-data publishing : a survey
Marco Fiore, Panagiota Katsikouli, Elli Zavou +7
We survey the literature on the privacy of trajectory micro-data, i.e., spatiotemporal information about the mobility of individuals, whose collection is becoming increasingly simp…
Fairwashing: the risk of rationalization
Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau +3
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Cur…