Accueil
Équipe
Publications
Open Source
Démos
Évènements
Blog
Carrières
Nous joindre
Français
Français
English
ServiceNow
ServiceNow IA recherche
Tags
Adversarial Attacks
ServiceNow IA recherche
Adversarial Attacks
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data …
Avinandan Bose
,
Laurent Lessard
,
Maryam Fazel
,
Krishnamurthy (Dj) Dvijotham
International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
PDF
Citation
Code
Vidéo
Constraining Representations Yields Models That Know What They Don't Know
A well-known failure mode of neural networks is that they may confidently return erroneous predictions. Such unsafe behaviour is …
João Monteiro
,
Pau Rodriguez
,
Pierre-André Noël
,
Issam H. Laradji
,
David Vazquez
International Conference of Learning Representations (ICLR), 2023.
PDF
Citation
Code
Model card
Diapositives
Vidéo
Maximal Jacobian-based Saliency Map Attack
The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural …
Rey Reza Wiyatno
,
Anqi Xu
Montreal AI Symposium (MAIS), 2018.
PDF
Citation
Code
Citation
×