Kernel Fusion for IoT Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to efficiently analyze and remediate hardware and software behavior in IoT devices, often due to resource-intensive methods that fail to detect imperceptible disruptions and require cumbersome configurations.
Innovation Solution
The described embodiments fuse computer code parameters with hardware performance data to form a kernel, which is then input into a trained model to detect execution performance anomalies, enabling rapid and tailored software and hardware remediation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional software and hardware analysis methods are used, then resource consumption is high, but detection accuracy and speed are insufficient
Solution Approach 1:
The patent combines software code parameters and hardware performance data into a unified kernel representation, merging previously separate analysis streams into a single integrated model input, thereby improving detection accuracy without proportionally increasing resource consumption
Solution Approach 2:
The patent creates simplified copies of complex system behavior through kernel representations that capture essential code and hardware characteristics without requiring full system state analysis, enabling efficient anomaly detection with reduced computing resources
2Measurement precision
If detailed code and hardware analysis is performed, then detection accuracy improves, but system complexity increases
Solution Approach 1:
The patent extracts only the essential features from code and hardware data to form kernels, separating critical information from unnecessary details, thereby maintaining detection accuracy while reducing system complexity
Solution Approach 2:
The patent transforms complex code and hardware parameters into a standardized kernel representation with consistent structure and dimensions, changing the parameter space to enable simpler model processing while preserving detection accuracy
3Reliability
If comprehensive hardware performance data is collected, then detection reliability improves, but data processing time increases
Solution Approach 1:
The patent performs preliminary processing of hardware performance data during normal operation to create pre-computed kernels, so that when anomalies need detection, the processing is already complete or near-complete, reducing response time while maintaining reliability
Solution Approach 2:
The patent collects more hardware performance data than strictly necessary (excessive action) but processes only the essential portions through the kernel representation, ensuring high detection reliability while keeping processing time acceptable through selective focus
Data Source
AI summary
Disclosed herein are techniques for detecting anomalous computing environment behavior. Techniques include fusing computer code parameters with hardware performance data associated with at least one device to form a kernel, the computer code parameters being associated with computer code configured for the at least one device; inputting the kernel to a trained model configured to detect execution performance anomalies of the at least one device, the trained model having been trained with a plurality of reference data patterns; and receiving, from the trained model, a detection output based on the kernel, the detection output indicating an anomalous behavior.