Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
This addresses the problem of adversarial robustness in 3D deep learning models, offering an incremental improvement in attack imperceptibility.
The paper tackled the challenge of balancing imperceptibility and effectiveness in adversarial attacks on 3D point clouds by introducing a point-to-surface field to adjust perturbation directions, resulting in more imperceptible attacks that outperform state-of-the-art methods.
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance imperceptibility with adversarial effectiveness. In this paper, we attribute the inadequate imperceptibility of adversarial attacks on point clouds to deviations from the underlying surface. To address this, we introduce a novel point-to-surface (P2S) field that adjusts adversarial perturbation directions by dragging points back to their original underlying surface. Specifically, we use a denoising network to learn the gradient field of the logarithmic density function encoding the shape's surface, and apply a distance-aware adjustment to perturbation directions during attacks, thereby enhancing imperceptibility. Extensive experiments show that adversarial attacks guided by our P2S field are more imperceptible, outperforming state-of-the-art methods.