发明名称 Self-tuning knowledge-based authentication
摘要 An improved technique involves automatically producing a set of KBA questions using values of attributes associated with correctly answered questions. A KBA question server obtains such attribute values from a prior set of pilot questions taken from users who were successfully authenticated. Examples of attributes include a source of facts in a question, placement of facts in a question, and question structure. The KBA question server then generates optimal formatting rules based on the attribute values; such formatting rules define a relationship between facts used to derive KBA questions and the words used to express the KBA questions to users. The KBA question generator then produces KBA questions according to the formatting rules.
申请公布号 US8850537(B1) 申请公布日期 2014.09.30
申请号 US201213628624 申请日期 2012.09.27
申请人 EMC Corporation 发明人 Dotan Yedidya;Villa Yael;Kronrod Boris
分类号 H04L29/06 主分类号 H04L29/06
代理机构 BainwoodHuang 代理人 BainwoodHuang
主权项 1. A method of generating knowledge-based authentication (KBA) questions from a set of facts, the method comprising: receiving, by a processor of a computer, answers to a first prior set of KBA questions from a group of users, each user of the group of users having been successfully authenticated using questions from a second prior set of KBA questions distinct from the first prior set of KBA questions, each KBA question of the first prior set of KBA questions having a format selected from a set of predefined formats, each format of the set of predefined formats defining a relationship between facts of the set of facts and words of a set of words in which the first prior set of KBA questions are expressed; identifying, by the processor, a correct subset of the first prior set of KBA questions to which the group of users provided correct answers and an incorrect subset of the first prior set of KBA questions to which the group of users provided incorrect answers; automatically selecting, by the processor, a first subset of the predefined set of formats based on the correct subset and a second subset of the predefined set of formats based on the incorrect subset; and generating, by the processor, a new set of KBA questions from facts of the set of facts, each KBA question of the new set of KBA questions having a format of the first subset of the predefined set of formats to improve effectiveness of future KBA questions.
地址 Hopkinton MA US