Neural Network Host Platform for Screenshot Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cybersecurity training modules face challenges in maintaining uniformity across various permutations, leading to undetected anomalies that result in visual defects and poor user experiences, which are difficult to address through manual review and consume significant computing resources.
Innovation Solution
A machine learning-based system using an auto-encoder and outlier detection algorithm to analyze screenshots of cybersecurity training modules, identifying and flagging anomalies for correction, and allowing for dynamic tuning based on user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual review methods are used to detect anomalies in training modules, then detection accuracy can be maintained, but time consumption and resource consumption increase significantly
Solution Approach 1:
The patent replaces manual visual review (mechanical process) with an automated machine learning system that uses auto-encoders and outlier detection algorithms to identify anomalies in training module permutations, significantly reducing time consumption while maintaining detection accuracy
Solution Approach 2:
The system performs self-testing by automatically generating permutations of training modules, capturing screenshots, and detecting anomalies without requiring human intervention in the testing process, thereby reducing both time and resource consumption
2Productivity
If automated anomaly detection systems are implemented, then productivity increases, but device complexity and computing resource requirements increase
Solution Approach 1:
The patent segments the anomaly detection process into distinct functional components: auto-encoder for normal permutation encoding, outlier detection algorithm for anomaly identification, and screenshot capture mechanisms, making the complex system modular and manageable
Solution Approach 2:
The patent introduces screenshots as an intermediary representation between the training module permutations and the anomaly detection algorithm, simplifying the complexity by converting complex module permutations into visual representations that can be easily processed and compared
3Manufacturing precision
If all permutations of training modules are tested to ensure uniformity, then manufacturing precision improves, but computing energy consumption increases
Solution Approach 1:
The patent applies partial action by using auto-encoders to process only the most critical permutation variations and using outlier detection algorithms that can identify anomalies without processing every possible permutation, thereby reducing energy consumption while maintaining sufficient uniformity checking
Solution Approach 2:
The patent changes the parameter of representation by converting training module permutations into screenshot images, which can be processed more efficiently by the auto-encoder and outlier detection algorithms, reducing the computational energy required compared to processing raw module data directly
Data Source
AI summary
Aspects of the disclosure relate to anomaly detection in cybersecurity training modules. A computing platform may receive information defining a training module. The computing platform may capture a plurality of screenshots corresponding to different permutations of the training module. The computing platform may input, into an auto-encoder, the plurality of screenshots corresponding to the different permutations of the training module, wherein inputting the plurality of screenshots corresponding to the different permutations of the training module causes the auto-encoder to output a reconstruction error value. The computing platform may execute an outlier detection algorithm on the reconstruction error value, which may cause the computing platform to identify an outlier permutation of the training module. The computing platform may generate a user interface comprising information identifying the outlier permutation of the training module. The computing platform may send the user interface to at least one user device.