Boosting 3D Adversarial Attacks With Attacking on Frequency
Open Access
- 2 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 50974-50984
Abstract
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a strong point cloud attack method named AOF which pays more attention to the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples and focus on the low-frequency component of point cloud in the process of optimization. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to state-of-the-art 3D defense methods. Otherwise, compared to adversarial point clouds generated by other adversarial attack methods, adversarial point clouds obtained by AOF contain more deformation than outlier. Code is available at: https://github.com/code-roamer/AOF .Keywords
All Related Versions
Funding Information
- Innovation Project of Guangxi Graduate Education (YCBZ2021019)
This publication has 29 references indexed in Scilit:
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- Frequency domain point cloud registration based on the Fourier transformJournal of Visual Communication and Image Representation, 2019
- Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction2018
- Boosting Adversarial Attacks with Momentum2018
- PU-Net: Point Cloud Upsampling Network2018
- Cluster-Based Point Cloud Coding with Normal Weighted Graph Fourier Transform2018
- Towards Evaluating the Robustness of Neural Networks2017
- 3D ShapeNets: A deep representation for volumetric shapes2015
- The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domainsIEEE Signal Processing Magazine, 2013
- Matrix Analysis1985