91 citations · 127 across the 18 of their papers we have counts for
5 papers · 1 filter
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
Mohamed Djilani, Thibault Simonetto, Karim Tit +4
Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, thei…
GIST: Generated Inputs Sets Transferability in Deep Learning
Florian Tambon, Foutse Khomh, Giuliano Antoniol
To foster the verifiability and testability of Deep Neural Networks (DNN), an increasing number of methods for test case generation techniques are being developed. When confronted…
Mutation Testing of Deep Reinforcement Learning Based on Real Faults
Florian Tambon, Vahid Majdinasab, Amin Nikanjam +2
Testing Deep Learning (DL) systems is a complex task as they do not behave like traditional systems would, notably because of their stochastic nature. Nonetheless, being able to ad…
How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
Florian Tambon, Gabriel Laberge, Le An +7
Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called 'safety-critical' systems such as automotive or aer…
HOMRS: High Order Metamorphic Relations Selector for Deep Neural Networks
Florian Tambon, Giulio Antoniol, Foutse Khomh
Deep Neural Networks (DNN) applications are increasingly becoming a part of our everyday life, from medical applications to autonomous cars. Traditional validation of DNN relies on…