Abstract: Methods, systems, and computer program products for providing the status of model extraction in the presence of colluding users are provided herein. A computer-implemented method includes generating, for each of multiple users, a summary of user input to a machine learning model; comparing the generated summaries to boundaries of multiple feature classes within an input space of the machine learning model; computing correspondence metrics based at least in part on the comparisons; identifying, based at least in part on the computed metrics, one or more of the multiple users as candidates for extracting portions of the machine learning model in an adversarial manner; and generating and outputting an alert, based on the identified users, to an entity related to the machine learning model.

Abstract: A wrapper builder application provides a variety of features for facilitating the creation of wrappers that are used to extract information from Web sites. In one aspect, the wrapper builder application provides a tool with which the process of creating a wrapper, which typically resembles coding, can be accomplished by a graphical design process involving drag and drop operations, clicking on objects, and filling in forms. A web viewer component provides a web browser frame, a source code frame, and a tree view frame, enabling the user to identify semistructured information of interest on Web sites. A wrapper editor component provides a graphical design environment in which a wrapper can be graphically constructed from operations and links. A wrapper model component provides a functioning internal representation of the graphically designed wrapper using Java objects and methods.