Abstract: A baseline request produced from an annotated node of a document object model (DOM) tree and a label assigned to the annotated node are obtained. The label is assigned to a set of neighboring nodes of the DOM that perform a same function by recursively causing the system to, for each neighboring node to the annotated node in the DOM tree an additional request produced in response to performance of simulated human interaction with the neighboring node is identified, if the additional request matches the baseline request, the label is assigned to the neighboring node, and the neighboring node is selected to be the annotated node.

Abstract: Source information for a set of interfaces from a service provider is collected. A generative adversarial network (GAN) is trained using the source information and the set of interfaces. The source information is provided to a generative network of the GAN. The generative network is caused to generate a simulated interface. A discriminative network of the GAN is caused, by providing the simulated interface to the discriminative network, to output an estimate as to the authenticity of the simulated interface. The generative network is trained, based on the estimate, to produce a trained generative network. The trained generative network is caused to generate a plurality of simulated interfaces. A machine learning model is trained, using the plurality of simulated interfaces, to determine how to interact with different types of interfaces.