Zobrazeno 11 - 20
of 2 167
pro vyhledávání: '"Fischer, Marc"'
Neural Ordinary Differential Equations (NODEs) are a novel neural architecture, built around initial value problems with learned dynamics which are solved during inference. Thought to be inherently more robust against adversarial perturbations, they
Externí odkaz:
http://arxiv.org/abs/2303.05246
Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language model can be used to automatically complete the sequence in a statist
Externí odkaz:
http://arxiv.org/abs/2212.06094
Neural networks pre-trained on a self-supervision scheme have become the standard when operating in data rich environments with scarce annotations. As such, fine-tuning a model to a downstream task in a parameter-efficient but effective way, e.g. for
Externí odkaz:
http://arxiv.org/abs/2211.09233
Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been la
Externí odkaz:
http://arxiv.org/abs/2210.15614
To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds for a small but carefully select
Externí odkaz:
http://arxiv.org/abs/2210.04871
Autor:
Lakhmi, Riadh1 (AUTHOR) marc.fischer@emse.fr, Fischer, Marc1 (AUTHOR), Darves-Blanc, Quentin1 (AUTHOR), Alrammouz, Rouba1 (AUTHOR), Rieu, Mathilde1 (AUTHOR), Viricelle, Jean-Paul1 (AUTHOR)
Publikováno v:
Sensors (14248220). Jun2024, Vol. 24 Issue 11, p3499. 23p.
Tree-based models are used in many high-stakes application domains such as finance and medicine, where robustness and interpretability are of utmost importance. Yet, methods for improving and certifying their robustness are severely under-explored, i
Externí odkaz:
http://arxiv.org/abs/2205.13909
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting their real-w
Externí odkaz:
http://arxiv.org/abs/2204.00487