Search Results for author: Adam Ivankay

Found 7 papers, 1 papers with code

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

1 code implementation5 Jul 2023 Adam Ivankay, Mattia Rigotti, Pascal Frossard

This results in our DomainAdaptiveAREstimator (DARE) attribution robustness estimator, allowing us to properly characterize the domain-specific robustness of faithful explanations.

Estimating the Adversarial Robustness of Attributions in Text with Transformers

no code implementations18 Dec 2022 Adam Ivankay, Mattia Rigotti, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Finally, with experiments on several text classification architectures, we show that TEA consistently outperforms current state-of-the-art AR estimators, yielding perturbations that alter explanations to a greater extent while being more fluent and less perceptible.

Adversarial Robustness text-classification +2

Fooling Explanations in Text Classifiers

no code implementations ICLR 2022 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

TEF can significantly decrease the correlation between unchanged and perturbed input attributions, which shows that all models and explanation methods are susceptible to TEF perturbations.

text-classification Text Classification

Artificial Intelligence Decision Support for Medical Triage

no code implementations9 Nov 2020 Chiara Marchiori, Douglas Dykeman, Ivan Girardi, Adam Ivankay, Kevin Thandiackal, Mario Zusag, Andrea Giovannini, Daniel Karpati, Henri Saenz

Applying state-of-the-art machine learning and natural language processing on approximately one million of teleconsultation records, we developed a triage system, now certified and in use at the largest European telemedicine provider.

FAR: A General Framework for Attributional Robustness

no code implementations14 Oct 2020 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Therefore, we define a novel generic framework for attributional robustness (FAR) as general problem formulation for training models with robust attributions.

Cannot find the paper you are looking for? You can Submit a new open access paper.