Factory Control Signal Monitoring for Malware Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Factory processes and equipment are vulnerable to sophisticated malware attacks that can disrupt operation and control, leading to severe impacts on output and equipment damage.
Innovation Solution
A computer-implemented method using a deep learning processor trained on data sets including input operating instructions and output control signals to detect anomalies in manufacturing processes, identifying deviations from expected values and providing indications of anomalous activity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional IT security processes are used to protect factory controllers, then basic security is maintained, but sophisticated malware attacks can still evade detection and cause subtle changes to operation and control
Solution Approach 1:
The patent replaces traditional mechanical IT security processes with a deep learning-based anomaly detection system. The deep learning processor analyzes relationships between input operating instructions and output control signals, automatically detecting anomalies without relying on predefined security rules or signatures, thereby detecting sophisticated malware that evades traditional security.
Solution Approach 2:
The patent introduces signal splitters as intermediaries to duplicate control signals and routing them to both the controller and the deep learning processor. This allows the security monitoring system to analyze control signals in real-time without interfering with the normal operation of the factory controller, maintaining system reliability while enhancing detection capability.
2Measurement precision
If deep learning processors are deployed to detect anomalies in control signals, then detection precision is improved, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary training of the deep learning processor offline using historical data containing normal and anomalous control signal patterns. This pre-trained model can then rapidly detect anomalies in real-time without requiring complex computations during operational monitoring, thus maintaining high detection precision while minimizing processing time delays.
3Reliability
If signal splitters are used to route control signals to the deep learning processor, then monitoring coverage is improved, but system complexity and potential failure points increase
Solution Approach 1:
The patent uses signal splitters to create duplicate copies of control signals, routing them to both the original controller and the deep learning processor simultaneously. This copying approach enables comprehensive monitoring coverage without modifying the original control system architecture, maintaining reliability while adding monitoring capability through non-intrusive signal duplication.
Data Source
AI summary
A training set that includes at least two data types corresponding to operations and control of a manufacturing process is obtained. A deep learning processor is trained to predict expected characteristics of output control signals that correspond with one or more corresponding input operating instructions. A first input operating instruction is received from a first signal splitter. A first output control signal is received from a second signal splitter. The deep learning processor correlates the first input operating instruction and the first output control signal. Based on the correlating, the deep learning processor determines that the first output control signal is not within a range of expected values based on the first input operating instruction. Responsive to the determining, an indication of an anomalous activity is provided as a result of detection of the anomalous activity in the manufacturing process.