One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation

arXiv:2404.02287v1 Announce Type: new
Abstract: This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images, offering a practical and scalable solution for enhancing model scalability and robustness. This generalizable method bridges the gap between 2D perturbations and 3D-like attack capabilities, making it suitable for real-world applications.
Existing adversarial attacks may become ineffective when images undergo transformations like changes …

3d object abstract adversarial adversarial attacks adversarial examples arxiv attacks cs.ai cs.cv examples images multiple noise novel object paper practical recognition robust scalability scalable solution them type universal view