Cruise Control Transfer Using Virtual Sensors Under ICS Attack
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial control systems are vulnerable to cyber-attacks, which can disrupt operations and cause significant economic or safety losses, and existing detection methods often result in costly or damaging emergency shutdowns, necessitating a more graceful approach to neutralizing attacks.
Innovation Solution
A method and system that utilize virtual sensor models to detect anomalies and transition industrial assets to a secondary operational mode using sensor readings from similar units, allowing for a smooth and controlled operation even when a critical node is under attack, thereby extending equipment life and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional emergency shutdown procedures are initiated upon detecting low confidence in critical node signal reconstruction, then the industrial asset is protected from suspected cyber-attacks, but significant economic loss and equipment life consumption occur
Solution Approach 1:
The system prepares multiple virtual sensor models in advance that can be activated when the primary sensor fails or is compromised. These pre-configured alternative models act as a cushion, allowing the system to maintain operation without immediate shutdown, thereby protecting equipment life while still addressing security threats.
Solution Approach 2:
The system creates virtual copies of sensor functionality through multiple virtual sensor models that replicate the behavior of the critical sensor. When the primary sensor is compromised, these virtual copies can take over, allowing continuous operation without emergency shutdown and preserving equipment life while maintaining security monitoring capabilities.
2Reliability
If traditional emergency shutdown procedures are initiated upon detecting low confidence in critical node signal reconstruction, then the industrial asset is protected from suspected cyber-attacks, but significant economic loss occurs
Solution Approach 1:
The system prepares multiple virtual sensor models in advance that can be activated when the primary sensor fails or is compromised. These pre-configured alternative models act as a cushion, allowing the system to maintain operation without immediate shutdown, thereby protecting equipment life while still addressing security threats.
Solution Approach 2:
The system creates virtual copies of sensor functionality through multiple virtual sensor models that replicate the behavior of the critical sensor. When the primary sensor is compromised, these virtual copies can take over, allowing continuous operation without emergency shutdown and preserving equipment life while maintaining security monitoring capabilities.
3Reliability
If multiple virtual sensor models are maintained and evaluated, then graceful attack neutralization is achieved, but system complexity increases
Solution Approach 1:
The system monitors confidence levels as a key parameter and uses threshold-based decision making to switch between virtual sensor models. This parameter-driven approach simplifies the management of multiple models by providing clear, automated criteria for model selection and switching, reducing the operational complexity despite having multiple models.
Solution Approach 2:
The system automatically evaluates confidence levels of multiple virtual sensor models and autonomously selects the most reliable model without requiring manual intervention. This self-service capability manages the complexity of multiple models through automated monitoring and switching, allowing the system to maintain high reliability while minimizing operational burden.
Data Source
AI summary
A procedure for neutralizing an attack on a control system of an industrial asset includes detecting an anomaly in a first sensor node associated with a first unit operating in a first operational mode, and receiving time series data associated with the first sensor node. A subset of the time series data is provided to each of a plurality of virtual sensor models A first virtual sensor model is selected from among a plurality of virtual sensor models based upon the subset of the time series data received by each of the plurality of virtual sensor models. A first confidence level of the first virtual sensor is determined. Responsive to determining that the first confidence level is below a first confidence level threshold, the first unit is transferred to a second operational mode using sensor readings associated with a second sensor node of a second unit of the industrial asset.