Computing Device Risk Prediction Using Probabilistic Security Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assessing the security risk of computing devices used in electronic commerce and e-government transactions are inaccurate and difficult to scale, leading to potential compromises of both devices and servers.
Innovation Solution
Utilizing a probabilistic graphical model, such as Bayesian or Markov networks, to systematically determine the risk level of a device by capturing dependencies between various security parameters, enabling improved accuracy and scalability in risk prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods are used to assess security risk, then the process is simple to implement, but the accuracy of risk assessment is poor
Solution Approach 1:
The security risk assessment is segmented into multiple independent security parameters (e.g., device integrity, network security, user behavior). Each parameter is evaluated separately using probability values, and then combined using a probabilistic graphical model. This segmentation allows for more accurate assessment while keeping each individual evaluation component manageable and modular.
Solution Approach 2:
A probabilistic graphical model serves as an intermediary between individual security parameter evaluations and the overall risk assessment. The model captures dependencies between parameters and computes the combined risk probability, enabling accurate assessment without requiring direct complex interactions between all parameters. The model acts as a mediator that systematically integrates multiple factors.
2Productivity
If existing methods are used to assess security risk, then the implementation is straightforward, but the method is difficult to scale to large numbers of devices
Solution Approach 1:
By segmenting the assessment into standardized security parameters that can be independently evaluated, the system can process multiple devices in parallel. Each device's security parameters are assessed using the same modular framework, enabling efficient scaling to large numbers of devices while maintaining consistent assessment quality.
Solution Approach 2:
The system uses probability values as parameters to represent security states, allowing for efficient computation and comparison across devices. The probabilistic graphical model enables rapid calculation of risk probabilities by changing and updating parameter values based on observed security conditions, making the assessment process highly scalable and adaptable to different device contexts.
3Reliability
If manual or heuristic methods are used to examine security parameters, then the system complexity is low, but the accuracy and reliability of risk detection is insufficient
Solution Approach 1:
The probabilistic graphical model incorporates feedback mechanisms where the assessment of one security parameter influences the evaluation of related parameters. The model continuously updates probability assignments based on observed security conditions and dependencies, improving the reliability of risk detection by considering the interconnected nature of security parameters rather than treating them in isolation.
Solution Approach 2:
The patent replaces manual or simple heuristic examination methods with a probabilistic graphical model that systematically computes risk probabilities. This substitution transitions from qualitative, intuition-based assessment to quantitative, mathematically-grounded evaluation, significantly improving reliability while the modular structure keeps the system complexity manageable through standardized parameter evaluation.
Data Source
AI summary
Disclosed herein are system, method, and computer program product embodiments for determining a probability of a device at risk. The device may be associated with a plurality of security parameters. For a security parameter, the device can be in multiple states. A probability value corresponding to a security parameter can indicate the security parameter being in a state among the multiple states. A probabilistic graphical model may be used to represent dependences of the plurality of security parameters. A device security risk prediction module may determine a probability of the device at risk based on the probabilistic graphical model and the probability assignments to the plurality of nodes of the probabilistic graphical model, and further determine a user action instruction to be provided to a user of the device based on the probability of the device at risk.