Abstract
3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep nets. Although most of these works consider adversarial attacks, we identify that backdoor attack is indeed a more serious threat to 3D deep learning systems but remains unexplored. We present the backdoor attacks in 3D with a unified framework that exploits the unique properties of 3D data and networks. In particular, we design two attack approaches: the poison-label attack and the clean-label attack. The first one is straightforward and effective in practice, while the second one is more sophisticated assuming there are certain data inspections. The attack algorithms are mainly motivated and developed by 1) the recent discovery of 3D adversarial samples which demonstrate the vulnerability of 3D deep nets under spatial transformations; 2) the proposed feature disentanglement technique that manipulates the feature of the data through optimization methods and its potential to embed a new task. Extensive experiments show the efficacy of the poison-label attack with over 95% success rate across several 3D datasets and models, and the ability of clean-label attack against data filtering with around 50% success rate. Our proposed backdoor attack in 3D point cloud is expected to perform as a baseline for improving the robustness of 3D deep models.
Abstract (translated)
URL
https://arxiv.org/abs/2103.16074
