Ronan Sicre

Papers

Total Citations

H-Index

About

Ronan Sicre is a researcher whose work lies at the intersection of computer vision, machine learning, and adversarial machine learning, with a particular focus on 3D point cloud analysis. His most notable contribution is the development of Eidos, a method for generating efficient and imperceptible adversarial 3D point clouds, which addresses critical vulnerabilities in 3D perception systems used in autonomous driving and robotics. This work, published in 2024, has already garnered attention for its practical implications in securing deep learning models against subtle, real-world attacks. While his citation count is still growing, Sicre’s research is positioned at the forefront of a rapidly evolving field, where the robustness of 3D vision systems is paramount. His contributions are particularly relevant for students and researchers exploring the security of neural networks in spatial environments, and his work on Eidos demonstrates a keen ability to balance theoretical rigor with applied impact. As the field of adversarial machine learning expands, Sicre’s insights into imperceptible perturbations in 3D data are likely to become increasingly influential.