对抗制
点云
利用
计算机科学
特征(语言学)
光学(聚焦)
水准点(测量)
人工智能
点(几何)
可转让性
深度学习
数据挖掘
功能(生物学)
人工神经网络
机器学习
深层神经网络
模式识别(心理学)
特征提取
钥匙(锁)
算法
卷积神经网络
作者
Shuchao Pang,Zhenghan Chen,Shen Zhang,Liming Lu,Siyuan Liang,Anan Du,Yongbin Zhou
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-10-19
卷期号:: 26912-26922
被引量:11
标识
DOI:10.1109/iccv51701.2025.02498
摘要
Deep neural networks for 3D point clouds have been demonstrated to be vulnerable to adversarial examples. Previous 3D adversarial attack methods often exploit certain information about the target models, such as model parameters or outputs, to generate adversarial point clouds. However, in realistic scenarios, it is challenging to obtain any information about the target models under conditions of absolute security. Therefore, we focus on transfer-based attacks, where generating adversarial point clouds does not require any information about the target models. Based on our observation that the critical features used for point cloud classification are consistent across different DNN architectures, we propose CFG, a novel transfer-based black-box attack method that improves the transferability of adversarial point clouds via the proposed Critical Feature Guidance. Specifically, our method regularizes the search of adversarial point clouds by computing the importance of the extracted features, prioritizing the corruption of critical features that are likely to be adopted by diverse architectures. Further, we explicitly constrain the maximum deviation extent of the generated adversarial point clouds in the loss function to ensure their imperceptibility. Extensive experiments conducted on the ModelNet40 and ScanObjectNN benchmark datasets demonstrate that the proposed CFG outperforms the state-of-the-art attack methods by a large margin.
科研通智能强力驱动
Strongly Powered by AbleSci AI