Utilizing 3D point cloud data has become an urgent need for the deployment of artificial intelligence in many areas like facial recognition and self-driving. However, deep learning for 3D point clouds is still vulnerable to adversarial attacks, e.g., iterative attacks, point transformation attacks, and generative attacks. These attacks need to restrict perturbations of adversarial examples within a strict bound, leading to the unrealistic adversarial 3D point clouds. In this paper, we propose an Adversarial Graph-Convolutional Generative Adversarial Network (AdvGCGAN) to generate visually realistic adversarial 3D point clouds from scratch. Specifically, we use a graph convolutional generator and a discriminator with an auxiliary classifier to generate realistic point clouds, which learn the latent distribution from the real 3D data. The unrestricted adversarial attack loss is incorporated in the special adversarial training of GAN, which enables the generator to generate the adversarial examples to spoof the target network. Compared with the existing state-of-art attack methods, the experiment results demonstrate the effectiveness of our unrestricted adversarial attack methods with a higher attack success rate and visual quality. Additionally, the proposed AdvGCGAN can achieve better performance against defense models and better transferability than existing attack methods with strong camouflage.
翻译:利用 3D 点云数据已成为在许多领域部署人工智能的迫切需要,如面部识别和自我驱动等。然而,对 3D 点云的深度学习仍然容易受到对抗性攻击,例如迭代攻击、点转换攻击和基因攻击。这些攻击需要限制在严格约束范围内对对抗性例子的扰动,导致不切实际的对立3D点云。在本文中,我们提议建立一个对立图形-动态组合生成反向网络(AdvGCGAN),以便从零开始产生现实的对抗性对立3D点云。具体地说,我们使用一个图形共振动生成器和一个带有辅助分类器的区分器来生成现实性的点云,从真实的3D数据中学习潜在分布。不受限制的对立性攻击损失被纳入GAN的特别对抗性训练,使发电机能够生成攻击性攻击网络的对立性实例。与现有的先进攻击性攻击方法相比,实验结果表明我们不受限制的对立性攻击性攻击性攻击性攻击方法的有效性,比现有的防御性强。 Adal AN 和视觉质量可以达到更好的防御性。