Factory Control Signal Monitoring for Malware Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Malware attacks on factory systems can cause subtle disruptions in manufacturing processes, evading traditional IT security measures and leading to equipment damage and yield loss by altering control parameters or providing false feedback, which existing monitoring systems fail to detect effectively.
Innovation Solution
A deep learning processor is trained on input operating instructions and output control signals to identify deviations from expected values, detecting anomalous activity and generating alerts for potential malware interference or other disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional IT security processes are used to monitor factory systems, then system simplicity is maintained, but detection precision of malware attacks deteriorates because malware can evade these processes
Solution Approach 1:
The patent introduces a deep learning processor as an intermediary component between the controller and the manufacturing process. This processor receives copies of input operating instructions and output control signals, analyzes them for anomalies using trained machine learning models, and generates alerts without interfering with the normal control flow. This intermediary approach enables advanced detection capabilities while maintaining the simplicity and reliability of the original control system.
2Reliability
If deep learning processors are added to monitor control signals, then detection precision improves, but device complexity increases
Solution Approach 1:
The monitoring function is segmented into a separate deep learning processor that operates independently from the main controller. The controller continues its primary function of executing manufacturing processes, while the deep learning processor handles the specialized task of anomaly detection by analyzing copies of control signals. This segmentation allows each component to specialize in its function without adding complexity to the other.
Solution Approach 2:
The system uses signal splitters to create copies of input operating instructions and output control signals. These copies are sent to the deep learning processor for analysis, while the original signals continue to the controller and process station. This copying mechanism enables monitoring without duplication of the entire control system, reducing complexity while maintaining detection capability.
3Manufacturing precision
If continuous monitoring of control signals is implemented, then manufacturing precision is maintained, but energy consumption increases
Solution Approach 1:
The deep learning processor performs periodic analysis of control signals at strategically chosen intervals rather than continuous monitoring. The system analyzes input operating instructions and output control signals at key transition points and periodic intervals, which maintains detection effectiveness while significantly reducing computational load and energy consumption compared to truly continuous analysis.
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.