Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks
Thibaut Boissin, Franck Mamalet, Valentin Lafargue +1
Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generativ…
cs.LG2025
Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
Valentin Lafargue, Adriana Laurindo Monteiro, Emmanuelle Claeys +2
The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for…