Spatio-temporal topology learning for suspicious access detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Physical access control systems face challenges in detecting and addressing security breaches and violations, such as fake cards or misused stolen cards, due to reliance on manual audits that consume time and resources and fail to guarantee detection of suspicious activities in a timely manner.
Innovation Solution
A spatio-temporal topology learning system that analyzes historical access control events to identify inconsistencies and flag potentially suspicious behavior by determining spatio-temporal properties associated with access pathways, including cardholder identity, resource access, time, and access point relationships, using a reachability graph and intelligent map of the facility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual audits of access logs are used to identify suspicious access events, then administrator experience and manual analysis can detect potential unlawful activities, but this approach consumes considerable amounts of time and resources and does not guarantee timely detection
Solution Approach 1:
The patent replaces the manual mechanical audit process with an automated computational system that uses machine learning models and algorithms to analyze access logs, thereby eliminating the time-consuming manual review while maintaining or improving detection accuracy through consistent application of detection criteria
Solution Approach 2:
The system enables self-service detection by automatically monitoring and analyzing access patterns without requiring administrator intervention for each audit cycle, allowing the system to autonomously identify suspicious activities and reduce the time burden on security personnel
2Speed
If static permission databases are used for access control decisions, then access decisions can be made quickly by checking credential permissions, but the system cannot detect suspicious behaviors such as fake cards or misused stolen cards
Solution Approach 1:
The patent introduces dynamic behavior analysis alongside static permission checking by continuously monitoring access patterns, timing, and sequences of credential usage, allowing the system to maintain fast access decisions while simultaneously detecting anomalies that indicate security breaches
Solution Approach 2:
The system implements feedback mechanisms where access decisions are continuously evaluated against learned patterns of normal and suspicious behavior, allowing the system to provide real-time feedback on potential security issues without slowing down the primary access control function
3Loss of information
If offline manual audits are performed to identify suspicious access activities, then potential security violations can be analyzed, but detection often occurs too late to address or limit damages of security breaches
Solution Approach 1:
The patent implements preliminary detection by continuously analyzing access patterns in near-real-time and identifying suspicious activities before they can cause significant damage, allowing security personnel to intervene proactively rather than reactively after breaches have occurred
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A spatio-temporal topology learning system for detection of suspicious access control behavior in a physical access control system (PACS). The spatio-temporal topology learning system including an access pathways learning module configured to determine a set of spatio-temporal properties associated with a resource in the PACS, an inconsistency detection module in operable communication with the access pathways learning module, the inconsistencies detection module configured to analyze a plurality of historical access control events and identify an inconsistency with regard to the set of spatio-temporal properties, and if an inconsistency is detected, at least one of the events is flagged as potentially suspicious access control behavior.