ANF: Crafting Transferable Adversarial Point Clouds via Adversarial Noise Factorization
- 2 August 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 11 (2) , 835-847
Abstract
Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate models and transferring them to other models to assess 3D model robustness. However, current methods rely too much on surrogate model parameters, limiting transferability. In this work, we use Shapley value to identify positive and negative features, guiding optimization of adversarial noise in feature space. To effectively mislead the 3D classifier, we factorize the adversarial noise into positive and negative noise, with the former keeping the features of the adversarial point cloud close to the negative features, and the latter and the adversarial noise moving it away from the positive features. Finally, a novel adversarial point cloud attack method with Adversarial Noise Factorization is proposed, which is abbreviated as ANF. ANF simultaneously optimizes the adversarial noise and its positive and negative noise in the feature space, only relying on partial network parameters, which significantly reduces the reliance on the surrogate model and improves the transferability of the adversarial point cloud. Experiments on well-recognized benchmark datasets show that the transferability of adversarial point clouds generated by ANF could be improved by more than 26.7$\%$ on average over state-of-the-art transfer-based adversarial attack methods.
Keywords
Funding Information
- National Natural Science Foundation of China (61876001)
- Natural Science Foundation of Anhui Province (1808085MF175)
- Scientific Research Planning Project of Anhui Province (2022AH050072)
This publication has 49 references indexed in Scilit:
- Improving transferability of 3D adversarial attacks with scale and shear transformationsInformation Sciences, 2024
- Adaptive local adversarial attacks on 3D point cloudsPattern Recognition, 2023
- ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning2022
- Boosting 3D Adversarial Attacks With Attacking on FrequencyIEEE Access, 2022
- Point TransformerIEEE Access, 2021
- PCT: Point cloud transformerComputational Visual Media, 2021
- AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds2020
- Transferable Adversarial Perturbations2018
- Scale-invariant heat kernel signatures for non-rigid shape recognition2010
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999