One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation
It addresses the challenge of adversarial attacks becoming ineffective under image transformations like lighting or camera changes, offering a practical solution for enhancing model robustness in real-world applications, though it appears incremental by extending single-view attacks to multi-view scenarios.
This paper tackles the problem of generating robust multi-view adversarial examples for 3D object recognition by developing a universal perturbation method that applies a single noise pattern to multiple 2D images from different viewpoints, lowering classification confidence across angles, especially at low noise levels.
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 in lighting, camera position, or natural deformations. We address this challenge by crafting a single universal noise perturbation applicable to various object views. Experiments on diverse rendered 3D objects demonstrate the effectiveness of our approach. The universal perturbation successfully identified a single adversarial noise for each given set of 3D object renders from multiple poses and viewpoints. Compared to single-view attacks, our universal attacks lower classification confidence across multiple viewing angles, especially at low noise levels. A sample implementation is made available at https://github.com/memoatwit/UniversalPerturbation.