论文标题
对抗机器学习研究的合成数据集生成
Synthetic Dataset Generation for Adversarial Machine Learning Research
论文作者
论文摘要
现有的对抗示例研究重点是在现有自然图像数据集之上进行数字插入的扰动。这种对抗性实例的构造是不现实的，因为攻击者由于感应和环境影响而在现实世界中部署这种攻击可能是困难的，甚至是不可能的。为了更好地理解针对网络物理系统的对抗性示例，我们提出了通过模拟近似现实世界的。在本文中，我们描述了我们的合成数据集生成工具，该工具可以可扩展收集具有逼真的对抗示例的合成数据集。我们使用CARLA模拟器收集此类数据集并演示与现实世界图像相同的环境变换和处理的模拟攻击。我们的工具已用于收集数据集，以帮助评估对抗性示例的功效，并可以在https://github.com/carla-simulator/carla/pull/4992上找到。
Existing adversarial example research focuses on digitally inserted perturbations on top of existing natural image datasets. This construction of adversarial examples is not realistic because it may be difficult, or even impossible, for an attacker to deploy such an attack in the real-world due to sensing and environmental effects. To better understand adversarial examples against cyber-physical systems, we propose approximating the real-world through simulation. In this paper we describe our synthetic dataset generation tool that enables scalable collection of such a synthetic dataset with realistic adversarial examples. We use the CARLA simulator to collect such a dataset and demonstrate simulated attacks that undergo the same environmental transforms and processing as real-world images. Our tools have been used to collect datasets to help evaluate the efficacy of adversarial examples, and can be found at https://github.com/carla-simulator/carla/pull/4992.
