Behavioral Input Pattern Verification for Unattended Secure Sessions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The security risk of unauthorized access to a computer system when a secure session is left unattended or credentials are compromised, as users often leave secure sessions open, leading to potential unauthorized access and misuse.
Innovation Solution
Implementing a security tool that captures usage patterns of authorized users on multiple input devices, utilizing a Machine Learning Model (MLM) to predict whether current user patterns match the authorized user profile, and implementing security measures when discrepancies are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a secure session is left open on the computer for extended periods, then user convenience is improved, but security risk increases as unauthorized users can potentially access the computer and secure session
Solution Approach 1:
The system performs preliminary actions by capturing usage pattern data during normal user operations and training the machine learning model in advance. This allows the security system to be ready to detect unauthorized users without interfering with the authorized user's convenience or requiring explicit security actions during normal operation.
Solution Approach 2:
The system continuously monitors usage patterns and compares them against the trained model, providing real-time feedback on whether the current user matches the authorized user profile. This feedback mechanism allows the system to maintain security while permitting uninterrupted operation for authorized users.
2Measurement precision
If traditional authentication methods like passwords or biometrics are used, then user identity verification is achieved, but security is compromised when credentials are stolen or session is left unattended
Solution Approach 1:
The usage pattern analysis acts as an intermediary verification layer between the user and the secure session. Instead of relying solely on static credentials, the system uses behavioral patterns as a mediator to continuously verify that the person operating the computer is the authorized user, even when the session is already established.
Solution Approach 2:
The system replaces the mechanical authentication system (passwords, biometrics) with a behavioral analysis system that continuously verifies user identity through usage patterns. This substitution allows for dynamic verification without requiring repeated explicit authentication actions from the user.
3Reliability
If a security tool monitors usage patterns in real-time, then unauthorized access detection is improved, but system complexity and processing requirements increase
Solution Approach 1:
The system creates a copy or model of the authorized user's behavior patterns through the trained machine learning model. This model can then be used for comparison without requiring complex real-time analysis of all raw input data, reducing processing requirements while maintaining detection accuracy.
Solution Approach 2:
The system transforms complex usage pattern data into simplified parameters or features that capture the essential characteristics of user behavior. By changing the representation of the data from raw input events to extracted behavioral parameters, the system reduces complexity while maintaining the ability to detect unauthorized users.
Data Source
AI summary
A computer system includes: a processor; a memory in communication with the processor; multiple user input devices; and a security tool to capture data defining usage patterns of an authorized user operating the multiple user input devices to prepare an authorized user profile and to implement security measures when usage patterns of a current user differ from the usage patterns of the authorized user from the profile. The security tool calls a Machine Learning Model (MLM) that is trained on the usage patterns of the authorized user from the profile, the MLM predicting for the security tool whether usage patterns of the current user indicate that the current user is not the authorized user based on the training of the MLM.