A Survey of Adversarial Example Toolboxes
Qingyuan Hu · 2021 2nd International Conference on Computing and Data Science (CDS) · 2021
At present, the development of artificial intelligence has attracted more and more attention, as one of the important branches of machine learning, deep learning has developed rapidly in recent years and received wide attention. However, in recent years, the concept of adversarial example has been put forward, more and more people began to pay attention to the security of deep learning, because the generation of adversarial example is helpful to improve the security of the model, so a variety of attack algorithms have been proposed and implemented by researchers. To make it easier for developers to use, many companies have built libraries to generate adversarial examples. This paper introduces these algorithms and tool libraries, and compares the configuration process of the tool library with the implementation of attack engineering, and puts forward a comprehensive selection proposal to the readers.