3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in the physical world, deep learning is notorious for its vulnerability to adversarial attacks. In this work, we first identify that the state-of-the-art empirical defense, adversarial training, has a major limitation in applying to 3D point cloud models due to gradient obfuscation. We further propose PointDP, a purification strategy that leverages diffusion models to defend against 3D adversarial attacks. We extensively evaluate PointDP on six representative 3D point cloud architectures, and leverage 10+ strong and adaptive attacks to demonstrate its lower-bound robustness. Our evaluation shows that PointDP achieves significantly better robustness than state-of-the-art purification methods under strong attacks. Results of certified defenses on randomized smoothing combined with PointDP will be included in the near future.
翻译:3D点云正在成为许多现实世界应用中的关键数据代表,如自主驾驶、机器人和医学成像。虽然深层次学习的成功进一步加快了物理世界对3D点云的采用,但深层次学习因其易受对抗性攻击而臭名昭著。在这项工作中,我们首先发现,由于梯度模糊,最先进的实证防御、对抗性训练在应用3D点云模型方面受到重大限制。我们进一步提议PointDP,即净化战略,利用扩散模型来防御3D对抗性攻击。我们广泛评价6个具有代表性的3D点云结构的点DP,并利用10+强力和适应性攻击来显示其强度较低。我们的评估表明,在猛烈攻击下,点DP比最先进的净化方法更强大得多。在随机滑动与点DP结合方面经认证的防御结果将在不久的将来列入。