Visa, border entry and security clearance interviews are critical homeland security activities that provide access privileges to the geographical United States or to classified information. The person conducting such an interview may not be an expert in the subject area or could be deceived by a manipulative interviewee, resulting in negative security consequences. This paper demonstrates how an interactive voice response system can be used to generate context-sensitive, yet randomized, dialogs that provide confidence in the trustworthiness of an interviewee based on his/her ability to answer questions. The system uses contextual reasoning and ontological inference to derive new facts dynamically. Item response theory is employed to create relevant questions based on social, environmental, relational and historical attributes related to interviewees who seek access to controlled areas or sensitive information.