We introduce AugLy, a data augmentation library with a focus on adversarial robustness. AugLy provides a wide array of augmentations for multiple modalities (audio, image, text, & video). These augmentations were inspired by those that real users perform on social media platforms, some of which were not already supported by existing data augmentation libraries. AugLy can be used for any purpose where data augmentations are useful, but it is particularly well-suited for evaluating robustness and systematically generating adversarial attacks. In this paper we present how AugLy works, benchmark it compared against existing libraries, and use it to evaluate the robustness of various state-of-the-art models to showcase AugLy's utility. The AugLy repository can be found at https://github.com/facebookresearch/AugLy.
翻译:我们引入了AugLy数据扩增图书馆, 重点是对抗性强力。 AugLy提供多种模式( 音频、 图像、 文本、 视频) 的多种增强功能。 这些增强功能的灵感来自真正的用户在社交媒体平台上完成的增强功能, 有些尚未得到现有数据扩增图书馆的支持。 AugLy 可用于数据扩增有用但特别适合于评估稳健性和系统生成对抗性攻击的任何目的。 在本文中,我们介绍AugLy是如何工作的,比照现有的图书馆,并利用它来评估各种最先进的模型展示AugLy的实用性。 AugLy 库可以在 https://github.com/facebookresearch/AugLy 上找到 。