Authentication Server Fraud Detection via Modified LSH
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional user authentication methods fail to detect fraudsters attempting to authenticate as multiple users from the same computer by only comparing current user authentication factors with previous factors from the same user, making it difficult to identify fraudulent activities.
Innovation Solution
An authentication server compares current user authentication factors with previously selected factors from multiple users using modified locally sensitive hashing (LSH) to identify close matches, allowing for the detection of fraudsters attempting to authenticate as different users while using the same computer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the authentication server compares current user authentication factors with previous factors from the same user only, then the authentication process is simple and fast, but the system fails to detect fraudsters attempting to authenticate as multiple users from the same computer
Solution Approach 1:
The patent segments the authentication process into two distinct phases: a filtering phase that quickly eliminates unrelated user profiles, and a detailed comparison phase that thoroughly checks only promising matches. This segmentation allows the system to expand the scope of detection without proportionally increasing overall complexity
Solution Approach 2:
The patent performs preliminary filtering of user profiles before conducting detailed authentication comparisons. By pre-processing and eliminating obviously unrelated profiles first, the system prepares the data in advance, reducing the computational burden of the subsequent detailed comparison phase
2Reliability
If the authentication server compares current user authentication factors with previous factors from multiple users, then the system can detect fraudsters attempting to authenticate as different users, but the number of comparisons increases significantly
Solution Approach 1:
The patent divides the comparison task into two segments: a rapid filtering segment that uses simplified criteria to eliminate unrelated profiles, and a detailed comparison segment that performs thorough authentication checks. This segmentation prevents the system from performing exhaustive comparisons on all user profiles
Solution Approach 2:
The patent applies partial action by performing only necessary comparisons - first a partial filter on all profiles, then complete comparisons only on the subset that passes the filter. This avoids the excessive action of comparing against every single user profile in the system
3Measurement precision
If the authentication server performs detailed comparison with all previous user authentication factors, then the detection accuracy is high, but the computational time and resources increase
Solution Approach 1:
The patent segments the authentication verification into a quick preliminary check phase and a detailed verification phase. The preliminary phase uses simplified criteria to rapidly filter out unrelated profiles, while the detailed phase applies comprehensive matching algorithms only to the small subset of profiles that pass the initial filter
Solution Approach 2:
The patent performs preliminary filtering of authentication profiles before conducting detailed comparisons. By pre-processing and eliminating obviously unrelated profiles first, the system reduces the number of computationally intensive detailed comparisons needed, thereby reducing overall processing time while maintaining accuracy
Data Source
AI summary
Techniques of performing authentication involve comparing current user authentication factors with previous authentication factors selected from multiple users during a single authentication session. Along these lines, suppose that an authentication server receives current browser characteristics from a user computer during a current authentication session. Based on the current browser characteristics, the authentication server selects previous browser characteristics received from devices used by multiple users during previous authentication sessions. For example, the authentication server may select previous browser characteristics based on the whether any of the results of a modified, locally sensitive hashing (LSH) of the previous browser characteristics match any of the results of a modified LSH of the current browser characteristics. After the authentication server selects the previous browser characteristics, the authentication server compares those selected, previous browser characteristics with the current browser characteristics.


