Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%

中文翻译：

---

LowKey：利用对抗攻击来保护社交媒体用户免受面部识别

私人公司，政府机构和承包商越来越多地将面部识别系统部署到消费者服务和大规模监视计划中。这些系统通常是通过抓取用户图像的社交媒体配置文件来构建的。已经提出了对抗扰动来绕过面部识别系统。但是，现有方法无法在全面系统和商业API上使用。我们开发了自己的对抗过滤器，该过滤器可处理整个图像处理管道，并且对包括人脸检测和大规模数据库在内的工业级管道具有明显的效果。此外，我们发布了易于使用的网络工具，该工具显着降低了Amazon Rekognition和Microsoft Azure Face Recognition API的准确性，从而将二者的准确性降低到1％以下