Efficient Joint Gradient Based Atack Against SOR Defense for 3D Point Cloud Classification
文献类型:会议论文
作者 | Chengcheng Ma; Weiliang Meng; Baoyuan Wu; Shibiao Xu; Xiaopeng Zhang |
出版日期 | 2020-10 |
会议日期 | October 12–16, 2020 |
会议地点 | Virtual |
英文摘要 | Deep learning based classifiers on 3D point cloud data have been shown vulnerable to adversarial examples, while a defense strategy named Statistical Outlier Removal (SOR) is widely adopted to defend adversarial examples successfully, by discarding outlier points in the point cloud. In this paper, we propose a novel white-box attack method, Joint Gradient Based Attack (JGBA), aiming to break the SOR defense. Specifically, we generate adversarial examples by optimizing an objective function containing both the original point cloud and its SOR-processed version, for the purpose of pushing both of them towards the decision boundary of classifier at the same time. Since the SOR defense introduces a non-differentiable optimization problem, we overcome the problem by introducing a linear approximation of the SOR defense and successfully compute the joint gradient. Moreover, we impose constraints on perturbation norm for each component point in the point cloud instead of for the entire object, to further enhance the attack ability against the SOR defense. Our JGBA method can be directly extended to the semi white-box setting, where the values of hyper-parameters in the SOR defense are unknown to the attacker. Extensive experiments validate that our JGBA method achieves the highest performance to break both the SOR defense and the DUP-Net defense (a recently proposed defense which takes SOR as its core procedure), compared with state-of-the-art attacks on four victim classifiers, namely PointNet, PointNet++(SSG), PointNet++(MSG), and DGCNN. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/47427] |
专题 | 模式识别国家重点实验室_三维可视计算 多模态人工智能系统全国重点实验室 |
通讯作者 | Shibiao Xu; Xiaopeng Zhang |
作者单位 | 1.School of Data Science, The Chinese University of Hong Kong, Shenzhen 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.NLPR, Institute ofAutomation, Chinese Academy of Sciences 4.Shenzhen Research Institute of Big Data 5.The State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Chengcheng Ma,Weiliang Meng,Baoyuan Wu,et al. Efficient Joint Gradient Based Atack Against SOR Defense for 3D Point Cloud Classification[C]. 见:. Virtual. October 12–16, 2020. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。