ICLR 2021
Workshop paper

Simple Transparent Adversarial Examples

Watch video


There has been a rise in the use of Machine Learning as a Service (MLaaS) Vision APIs as they offer multiple services including pre-built models and algorithms, which otherwise take a huge amount of resources if built from scratch. As these APIs get deployed for high-stakes applications, it’s very important that they are robust to different manipulations. Recent works have only focused on typical adversarial attacks when evaluating the robustness of vision APIs. We propose two new aspects of adversarial image generation methods and evaluate them on the robustness of Google Cloud Vision API’s optical character recognition service and object detection APIs deployed in real-world settings such as,, Google Cloud Vision API, and Microsoft Azure’s computer vision API. Specifically, we go beyond the conventional “small-noise” adversarial attacks and introduce secret embedding and transparent adversarial examples as a simpler way to evaluate robustness. These methods are so straightforward that even nonspecialists can craft such attacks. As a result, they pose a serious threat where APIs are used for high-stakes applications. Our transparent adversarial examples successfully evade state-of-the-art object detection APIs such as Azure Cloud Vision (attack success rate 52%) and Google Cloud Vision (attack success rate 36%). 90% of the images have a secret embedded text that successfully fools the vision of time-limited humans but is detected by Google Cloud Vision API’s optical character recognition. Complementing to current research, our results provide simple but unconventional methods on robustness evaluation.


03 May 2021


ICLR 2021