TPC: Transformation-Specific Smoothing for Point Cloud Models

INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162(2022)

引用 11|浏览46
暂无评分
摘要
Point cloud models with neural network architectures have achieved great success and have been widely used in safety-critical applications, such as Lidar-based recognition systems in autonomous vehicles. However, such models are shown to be vulnerable to adversarial attacks that aim to apply stealthy semantic transformations such as rotation and tapering to mislead model predictions. In this paper, we propose a transformationspecific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks. We first categorize common 3D transformations into three categories: additive (e.g., shearing), composable (e.g., rotation), and indirectly composable (e.g., tapering), and we present generic robustness certification strategies for all categories respectively. We then specify unique certification protocols for a range of specific semantic transformations and their compositions. Extensive experiments on several common 3D transformations show that TPC significantly outperforms state of the art. For example, our framework boosts the certified accuracy against twisting transformation along the z-axis (within +/- 20 degrees) from 20.3% to 83.8%. Codes and models are available at https://github.com/ Qianhewu/Point- Cloud- Smoothing.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要