Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionElectrical Engineering Program
VCC Analytics Research Group
Visual Computing Center (VCC)
KAUST Grant Number
RGC/3/3570-01-01Date
2020-10-07Preprint Posting Date
2019-12-01Online Publication Date
2020-10-07Print Publication Date
2020Embargo End Date
2021-10-06Permanent link to this record
http://hdl.handle.net/10754/665816
Metadata
Show full item recordAbstract
Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous network predictions. This phenomenon has been extensively studied in the image domain, and has only recently been extended to 3D point clouds. In this work, we present novel data-driven adversarial attacks against 3D point cloud networks. We aim to address the following problems in current 3D point cloud adversarial attacks: they do not transfer well between different networks, and they are easy to defend against via simple statistical methods. To this extent, we develop a new point cloud attack (dubbed AdvPC) that exploits the input data distribution by adding an adversarial loss, after Auto-Encoder reconstruction, to the objective it optimizes. AdvPC leads to perturbations that are resilient against current defenses, while remaining highly transferable compared to state-of-the-art attacks. We test AdvPC using four popular point cloud networks: PointNet, PointNet++ (MSG and SSG), and DGCNN. Our proposed attack increases the attack success rate by up to 40% for those transferred to unseen networks (transferability), while maintaining a high success rate on the attacked network. AdvPC also increases the ability to break defenses by up to 38% as compared to other baselines on the ModelNet40 dataset. The code is available at https://github.com/ajhamdi/AdvPC.Citation
Hamdi, A., Rojas, S., Thabet, A., & Ghanem, B. (2020). AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds. Lecture Notes in Computer Science, 241–257. doi:10.1007/978-3-030-58610-2_15Sponsors
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research under Award No. RGC/3/3570-01-01.Publisher
Springer NatureConference/Event name
16th European Conference on Computer Vision, ECCV 2020ISBN
9783030586096arXiv
1912.00461Additional Links
http://link.springer.com/10.1007/978-3-030-58610-2_15Relations
Is Supplemented By:- [Software]
Title: ajhamdi/AdvPC: AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020). Publication Date: 2019-08-26. github: ajhamdi/AdvPC Handle: 10754/668128
ae974a485f413a2113503eed53cd6c53
10.1007/978-3-030-58610-2_15