activity
20172024
most citedImperceptible Adversarial Attacks on Tabular Data

50 citations · 124 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2024

Post-processing fairness with minimal changes

Federico Di Gennaro, Thibault Laugel, Vincent Grari +2

In this paper, we introduce a novel post-processing algorithm that is both model-agnostic and does not require the sensitive attribute at test time. In addition, our algorithm is e…

cs.LG20211 cited

How to choose an Explainability Method? Towards a Methodical Implementation of XAI in Practice

Tom Vermeire, Thibault Laugel, Xavier Renard +2

Explainability is becoming an important requirement for organizations that make use of automated decision-making due to regulatory initiatives and a shift in public awareness. Vari…

cs.LG20213 cited

Understanding surrogate explanations: the interplay between complexity, fidelity and coverage

Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2

This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings. We start our exposition by considering glob…

cs.LG20213 cited

On the overlooked issue of defining explanation objectives for local-surrogate explainers

Rafael Poyiadzi, Xavier Renard, Thibault Laugel +2

Local surrogate approaches for explaining machine learning model predictions have appealing properties, such as being model-agnostic and flexible in their modelling. Several method…

cs.LG2019

The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations

Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala +2

Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the…

cs.LG201921 cited

Issues with post-hoc counterfactual explanations: a discussion

Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala +1

Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the…