Publications

Affichage de 331 à 340 sur 16133


  • Chapitre d'ouvrage

XAI for wireless communications

Abdul-Karim Gizzini, Yahia Medjahdi, Ali Ghandour, Laurent Clavier, Mouna Ben Mabrouk

The native artificial intelligence (AI) concept is envisioned to be integrated into 6G future communications. Due to the black box nature of the majority of AI models, the decision-making strategy used by these models is critical, risky, and challenging. This issue can be tackled by developing…

Explainable AI for Communications and Networking, Elsevier, pp.73-91, 2025, 9780443291357. ⟨10.1016/B978-0-44-329135-7.00014-X⟩. ⟨hal-05264870⟩

  • Article dans une revue

Locally sealed microfabricated vapor cells filled from an ex situ Cs source

Linda Peroux, Arthur Dewilde, Ravinder Kumar Chutani, Aurelien Mazzamurro, Jérémy Bonhomme, Andrei Mursa, Jean-François Clément, Abdelkrim Talbi, Philippe Pernod, Nicolas Passilly, Vincent Maurice

Microfabricated alkali vapor cells are key to enable miniature devices such as atomic clocks and optically pumped magnetometers with reduced size, weight and power. Yet, more versatile fabrication methods are still needed to further expand their use cases. Here, we demonstrate a novel approach to…

Applied Physics Letters, 2025, 126 (14), pp.144003. ⟨10.1063/5.0265624⟩. ⟨hal-05057374⟩

  • Communication dans un congrès

SnatchML: Hijacking ML Models Without Training Access

Mahmoud Ghorbel, Halima Bouzidi, Ioan Marius Bilasco, Ihsen Alouani

The widespread deployment of Machine Learning (ML) models has been accompanied by the emergence of various attacks that threaten their trustworthiness and raise ethical and societal concerns. One such attack is model hijacking, where an adversary seeks to repurpose a victim model to perform a…

2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Apr 2025, Copenhagen, Denmark. pp.92-109, ⟨10.1109/SaTML64287.2025.00013⟩. ⟨hal-05148276⟩