Google has recently introduced the Cloud Vision API for image analysis. According to the demonstration website, the API "quickly classifies images into thousands of categories, detects individual objects and faces within images, and finds and reads printed words contained within images." It can be also used to "detect different types of inappropriate content from adult to violent content." In this paper, we evaluate the robustness of the Google's Cloud Vision API to input perturbation. In particular, we show that by adding sufficient noise to the image, the API generates completely different outputs for the noisy image, while a human observer would perceive its original content. We show that the attack is consistently successful, by performing extensive experiments on different image types, including natural images, images containing faces and images with texts. Our findings indicate the vulnerability of the API in adversarial environments. For example, an adversary can bypass an image filtering system by adding noise to an image with inappropriate content.

本文评估了Google Cloud Vision API对图像摄动输入的鲁棒性，并证明添加足够的噪音到图像中能够欺骗该API的分类器，从而证明了该API在对抗性环境中的脆弱性，并建议采用噪声过滤的方式改善该API的图像分析能力。

Google Cloud Vision API 对噪声不够稳健