Self-tuning KBA Authentication via Automated Pilot Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional knowledge-based authentication (KBA) systems that use pilot questions for feedback require manual evaluation by administrators, exposing sensitive information and risking errors, which is impractical for corporations lacking resources and increases the risk of information exposure.
Innovation Solution
Automating the analysis of pilot question results by determining communication factors such as font, fact source, and voice structure to generate new KBA questions, minimizing false negatives and allowing internal handling of feedback data without third-party expertise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual evaluation of pilot questions is used, then authentication effectiveness can be assessed, but sensitive information may be exposed and human errors occur
Solution Approach 1:
The KBA system automatically evaluates pilot question effectiveness using computational algorithms that analyze user responses and determine question quality metrics, eliminating the need for manual administrator evaluation and the associated information exposure risks
Solution Approach 2:
Manual human evaluation processes are replaced with automated computational systems that use algorithms to assess pilot question performance, removing human administrators from the evaluation loop and eliminating risks of human error and information exposure
2Object-affected harmful factors
If manual evaluation by internal administrators is used, then information security is maintained, but resource requirements increase and errors remain risky
Solution Approach 1:
The system performs self-evaluation of pilot questions through automated computational processes, eliminating the need for internal administrator resources while maintaining information security and removing human error risks
Solution Approach 2:
Human administrator evaluation resources are replaced with automated computational systems that efficiently assess pilot question effectiveness without consuming human resources or introducing errors
3Reliability
If pilot questions are used for authentication, then user verification is performed, but false negatives may occur due to ineffective question formats
Solution Approach 1:
The system uses pilot question results as feedback to automatically identify and eliminate question formats that produce false negatives, continuously improving authentication accuracy by analyzing which formats legitimate users answer incorrectly
Solution Approach 2:
The system changes question format parameters (communication factors) based on pilot question performance data, automatically selecting formats that minimize false negatives while maintaining authentication security
Data Source
AI summary
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.