
Facial expression recognition models can be misled by subtle adversarial attacks that preserve the surface structure of 3D faces.


coremsg

ϵ-mesh-attack-a-surface-based-adversarial-point-cloud-attack-for-facial-expression-recognition


ϵ-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition


title_rewrite


Facial expression recognition models can be misled by subtle adversarial perturbations on point clouds, highlighting the importance of preserving surface structure in 3D data.



Das ϵ-Mesh Attack ist eine innovative Methode für 3D-Gesichtserkennungsmodelle, die die Oberflächenstruktur bewahrt und die Leistung von Deep Learning-Modellen beeinträchtigt.


ϵ-mesh-attack-a-surface-based-adversarial-point-cloud-attack-for-facial-expression-recognition-at-fg-2024-conference


ϵ-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition at FG 2024 Conference
