4 papers
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…
Probing Cultural Signals in Large Language Models through Author Profiling
Valentin Lafargue, Ariel Guerra-Adames, Emmanuelle Claeys +2
Large language models (LLMs) are increasingly deployed in applications with societal impact, raising concerns about the cultural biases they encode. We probe these representations…
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…
Fairness is in the details: Face Dataset Auditing
Valentin Lafargue, Emmanuelle Claeys, Jean-Michel Loubes
Auditing involves verifying the proper implementation of a given policy. As such, auditing is essential for ensuring compliance with the principles of fairness, equity, and transpa…