papers

Publications (7)

cs.LG2023

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

Adam Ivankay, Mattia Rigotti, Pascal Frossard

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant incre…

cs.LG2024

Auditing and Generating Synthetic Data with Controllable Trust Trade-offs

Brian Belgodere, Pierre Dognin, Adam Ivankay +11

Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate…

cs.AI2020

Artificial Intelligence Decision Support for Medical Triage

Chiara Marchiori, Douglas Dykeman, Ivan Girardi +6

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…

cs.LG2022

Fooling Explanations in Text Classifiers

Adam Ivankay, Ivan Girardi, Chiara Marchiori +1

State-of-the-art text classification models are becoming increasingly reliant on deep neural networks (DNNs). Due to their black-box nature, faithful and robust explanation methods…

cs.LG2022

Estimating the Adversarial Robustness of Attributions in Text with Transformers

Adam Ivankay, Mattia Rigotti, Ivan Girardi +2

Explanations are crucial parts of deep neural network (DNN) classifiers. In high stakes applications, faithful and robust explanations are important to understand and gain trust in…

cs.LG2022

FAR: A General Framework for Attributional Robustness

Adam Ivankay, Ivan Girardi, Chiara Marchiori +1

Attribution maps are popular tools for explaining neural networks predictions. By assigning an importance value to each input dimension that represents its impact towards the outco…