Generating Unrestricted 3D Adversarial Point Clouds

11/17/2021
by   Xuelong Dai, et al.
0

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.

READ FULL TEXT
research
01/26/2022

Boosting 3D Adversarial Attacks with Attacking On Frequency

Deep neural networks (DNNs) have been shown to be vulnerable to adversar...
research
02/27/2020

Defense-PointNet: Protecting PointNet Against Adversarial Attacks

Despite remarkable performance across a broad range of tasks, neural net...
research
08/27/2020

Minimal Adversarial Examples for Deep Learning on 3D Point Clouds

With the recent developments of convolutional neural networks, deep lear...
research
12/24/2019

Geometry-aware Generation of Adversarial and Cooperative Point Clouds

Recent studies show that machine learning models are vulnerable to adver...
research
11/14/2021

Generating Band-Limited Adversarial Surfaces Using Neural Networks

Generating adversarial examples is the art of creating a noise that is a...
research
05/18/2022

Passive Defense Against 3D Adversarial Point Clouds Through the Lens of 3D Steganalysis

Nowadays, 3D data plays an indelible role in the computer vision field. ...
research
09/16/2022

PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition

Notwithstanding the prominent performance achieved in various applicatio...

Please sign up or login with your details

Forgot password? Click here to reset