Abstract: Techniques are described herein that are capable of selectively authenticating a user using voice recognition and random representations. A credential that is received from an entity is compared to a reference credential associated with a user. The random representations are caused to be displayed to the entity based at least in part on the credential corresponding to the reference credential. Each random representation has a random entropy. A representation of speech of the entity is analyzed to determine whether a voice characterized by the speech corresponds to a voice profile that characterizes a voice of the user and to determine whether the speech includes a verbal identification of each random representation. The user is selectively authenticated based at least in part on whether the voice corresponds to the voice profile and further based at least in part on whether the speech includes the verbal identification of each random representation.