Knowledge-Based Authentication Fraud Detection via Silent-Alarm Encoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Knowledge-based authentication (KBA) systems are vulnerable to brute-force and dictionary attacks due to the use of secrets with low entropy, making them susceptible to fraud, especially with the increasing availability of personal information through social engineering and data mining.

Innovation Solution

Implementing a silent-alarm knowledge-based authentication method that uses encoding schemes and confidence scoring to assess the credibility of user responses, incorporating historical, inter-relational, and contextual information to differentiate between legitimate and fraudulent access attempts, without requiring modifications to existing applications or communication protocols.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If KBA uses secrets with low entropy for easy recall, then user convenience is improved, but security against brute-force attacks deteriorates

Engineering Contradiction:
Improveuser recall abilityVSAvoidsecurity against brute-force attacks
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary actions by establishing encoding schemes and confidence thresholds before authentication attempts occur. The server prepares encoding rules (such as reverse alphabet, Caesar cipher, or substitution mappings) and confidence score thresholds in advance, so that when authentication occurs, the system can immediately detect fraudulent attempts without requiring complex real-time analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by calculating confidence scores for each authentication response and comparing them against predetermined thresholds. The server provides feedback on whether the response appears authentic or fraudulent based on the confidence score, and can trigger remediation actions when fraud is detected. This closed-loop feedback enables continuous security monitoring and adaptation.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If KBA relies on personal information from public records, then answer discoverability by attackers increases, but user memory burden decreases

Engineering Contradiction:
Improveanswer memorabilityVSAvoidvulnerability to data mining attacks
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system introduces an intermediary encoding layer between the user's personal information and the authentication challenge. Instead of directly using personal information from public records, the system applies encoding schemes (reverse alphabet, Caesar cipher, substitution mappings) that transform the information into a form that is difficult for attackers to discover through data mining, while still allowing the legitimate user to provide correct answers.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the parameters of the authentication data by applying various encoding transformations to the personal information. These parameter changes (different encoding schemes, confidence thresholds, and response validations) modify the characteristics of the authentication data to resist attacks while maintaining usability for legitimate users.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If KBA uses simple encoding schemes, then implementation complexity is reduced, but fraud detection capability deteriorates

Engineering Contradiction:
Improveencoding scheme complexityVSAvoidfraud detection accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system segments the fraud detection process into multiple independent components: encoding scheme selection, confidence score calculation, threshold comparison, and remediation triggering. Each component can be implemented and validated separately, reducing overall implementation complexity while maintaining comprehensive fraud detection capability through the combination of these segmented functions.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9021553B1Methods and apparatus for fraud detection and remediation in knowledge-based authentication
Publication Date: 2015.04.28 EMC IP HLDG CO LLC
  • US9021553B1 patent drawing
  • US9021553B1 patent drawing
  • US9021553B1 patent drawing

AI summary

Methods and apparatus are provided for fraud detection and remediation in knowledge-based authentication (KBA). A knowledge-based authentication method is performed by a server for restricting access of a user to a restricted resource. The exemplary knowledge-based authentication method comprises challenging the user with one or more questions requiring knowledge by the user; receiving a response from the user to the one or more questions, wherein at least a portion of the response is encoded by the user using an encoding scheme defined between the server and the user to signal a fraudulent access attempt; and granting access to the restricted resource if one or more predefined response criteria are satisfied, wherein the one or more predefined response criteria comprises an assessment of whether the encoded portion of the response satisfies the encoding scheme. A number of exemplary encoding schemes are disclosed.