Title | ||
---|---|---|
A physically realizable backdoor attack on 3D point cloud deep learning: work-in-progress |
Abstract | ||
---|---|---|
ABSTRACTModern autonomous driving has widely used deep learning to process point cloud data. This application is widely deployed on embedded edge computing devices and has high security requirements. We found that backdoor attacks can pose an extremely serious threat to point cloud deep learning systems, but this attack method has not been explored in point cloud deep learning tasks. In this paper, we propose a physically implementable backdoor attack method for the point cloud deep learning model. This method can achieve good performance in the attack effect and physical realization, evaluating by preliminary experiments. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1145/3478684.3479254 | ESWEEK |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Bian | 1 | 0 | 1.35 |
Wei Jiang | 2 | 5 | 2.81 |
Jinyu Zhan | 3 | 3 | 8.15 |
Ziwei Song | 4 | 1 | 2.04 |
Xiangyu Wen | 5 | 1 | 2.05 |
Hong Lei | 6 | 0 | 0.34 |