Device-to-Account Anomaly Detection via Locality-Sensitive Hashing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Insecure device-to-account associations in smart environments lead to security breaches and hindered functionality due to discrepancies in device identifier information stored between user registries and remote systems, causing anomalies that are not effectively addressed by existing technologies.
Innovation Solution
A system and method for device-to-account anomaly detection that queries remote systems for device identifier information, generates hash values using locality-sensitive hashing to compare with user registry data, and takes corrective actions based on detected anomalies, utilizing machine learning models to determine causes and select appropriate actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If device identifier information is stored in both user registries and remote systems, then device-to-account associations can be maintained, but discrepancies and anomalies arise leading to security breaches
Solution Approach 1:
The system performs preliminary anomaly detection by comparing device identifier information between user registries and remote systems before security breaches can occur. The anomaly detection component proactively identifies discrepancies in device-to-account associations and triggers corrective actions to prevent security compromises.
Solution Approach 2:
The system implements feedback mechanisms where the anomaly detection component continuously monitors device identifier information, compares it against stored user registry data, and provides feedback about discrepancies. This feedback loop enables the system to detect and correct anomalies that could lead to security breaches.
2Reliability
If device identifier information is queried from remote systems, then anomalies can be detected, but system complexity increases
Solution Approach 1:
The system introduces an intermediary anomaly detection component that mediates between the user registry and remote systems. This intermediary layer handles the complexity of querying, comparing, and analyzing device identifier information, thereby detecting anomalies without significantly increasing overall system complexity.
Solution Approach 2:
The anomaly detection system is segmented into distinct functional components: a query component that retrieves device information from remote systems, a comparison component that analyzes discrepancies, and a corrective action component that responds to anomalies. This segmentation manages system complexity by dividing the detection task into manageable modules.
3Reliability
If corrective actions are taken based on detected anomalies, then security is enhanced, but response time and processing speed are reduced
Solution Approach 1:
The system prepares corrective actions in advance based on detected anomalies. The anomaly detection component identifies issues and triggers pre-planned corrective measures, reducing the time needed to respond to security threats while maintaining thorough security protection.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Effectively identifies and mitigates device-to-account anomalies, enhancing security and functionality by ensuring accurate device associations and reducing the risk of security breaches through proactive anomaly detection and correction.
Implementation Method 1
generates hash values using locality-sensitive hashing to compare with user registry data
Data Source
AI summary
Systems and methods for device-to-account anomaly detection are disclosed. For example, device information associated with user account data is queried from a user registry and from an external system. The device information from both sources is hashed or otherwise formatted and compared to determine whether a dissimilarity is present. A difference value may be generated and utilized to determine whether an anomaly is present for device-to-account associations as between the user registry and the external system. Utilizing the difference value and/or historical difference values associated with the external system, one or more actions for correcting the anomaly may be selected and performed.