PropScreen

PropScreen is a contraction of the words "proprietary" and "screen" and is named such because the primary function of Propscreen is to screen outputs from LLMs that have been trained on proprietary organizational data or other data that an organization has deemed to be sensitive. These outputs are screened in a manner such that if a user is going to receive a response that discloses data that is in violation of organizational policy, the response is interdicted and the user receives an error message instead.

In its current iteration, PropScreen has two primary functionalities: the interdiction of sensitive information and the generation of logs based on those interdictions. Sensitive information interdiction occurs by passing the LLM's responses through a series of three possible checks: a check against general schemas of sensitive information by means of an SLM provided by LLM Guard, a check of the model response against a database of words set by the organization trigger further inquiry, and finally if either one of the two previous checks yields a detection of sensitive information; a check against a database of the hashed sensitive information.

The contextual database and hashes database empower an organization to deterministically prevent sensitive information specific to the company form being disclosed to unauthorized parties.